diff --git a/gpt2-medium/ArXiv/lambda_0.0/model/config.json b/gpt2-medium/ArXiv/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_0.0/model/generation_config.json b/gpt2-medium/ArXiv/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_0.0/model/model.safetensors b/gpt2-medium/ArXiv/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..008c3fd4c2fe182ae316482bf141ccb721cdfced --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7d947c4c64bf94998caf627bf57e33ce7ffe6a783dbba6e402d44ffd3ca79e +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_0.0001/model/config.json b/gpt2-medium/ArXiv/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_0.0001/model/generation_config.json b/gpt2-medium/ArXiv/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_0.0001/model/model.safetensors b/gpt2-medium/ArXiv/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..827ab4778c1e4da2b5480a38b3db6b46906d589d --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b00c3bb5925d8b85bc5f2f8ee7952ec709848dcc80411078fc8f1a089311fcf6 +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_0.001/model/config.json b/gpt2-medium/ArXiv/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_0.001/model/generation_config.json b/gpt2-medium/ArXiv/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_0.001/model/model.safetensors b/gpt2-medium/ArXiv/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..61109d42c444fa83af5388f884cf438c3010576c --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a556fab74c38856df6f580c28f0b3db72b78efcfffe56c542bc42fc8dfcfe489 +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_0.01/model/config.json b/gpt2-medium/ArXiv/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_0.01/model/generation_config.json b/gpt2-medium/ArXiv/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_0.01/model/model.safetensors b/gpt2-medium/ArXiv/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b120b6ca0866f54f794e466dc7b7f14f2193a36c --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c2214e9265290603191e5d4b21cf6b939b93a85c2c7019988a8e189f7bc4a1 +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_0.1/model/config.json b/gpt2-medium/ArXiv/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_0.1/model/generation_config.json b/gpt2-medium/ArXiv/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_0.1/model/model.safetensors b/gpt2-medium/ArXiv/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4805fc8830de5b04dec44b7c123600f9ff37726e --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75d40a78594380efbe481c9a249bcec2bdcf2bd8991ef05d78bcbe31b74b7604 +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_0.3/model/config.json b/gpt2-medium/ArXiv/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_0.3/model/generation_config.json b/gpt2-medium/ArXiv/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_0.3/model/model.safetensors b/gpt2-medium/ArXiv/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a4de8ae2f2dad2ab7977432d31e670db7a10522d --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c70dbd2877a6d29a31e1103b7754dc32de5081153275e81d9a77b3853d9b74 +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_0.5/model/config.json b/gpt2-medium/ArXiv/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_0.5/model/generation_config.json b/gpt2-medium/ArXiv/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_0.5/model/model.safetensors b/gpt2-medium/ArXiv/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eec948d8775d3d7b429f8ce3ffb9ff5e9549f7c8 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6332e997971a42886df87a0b913a2bcbe8d8b51b47613adf15ea4a7256be470a +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_1.0/model/config.json b/gpt2-medium/ArXiv/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_1.0/model/generation_config.json b/gpt2-medium/ArXiv/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_1.0/model/model.safetensors b/gpt2-medium/ArXiv/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96ef4839970a3fc7da57b7c9b07f58d4ffff5398 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed1d52eef4833891da2b4ef114bb82e4299b074be23a6b88e3dc345406cb5649 +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_1e-05/model/config.json b/gpt2-medium/ArXiv/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_1e-05/model/generation_config.json b/gpt2-medium/ArXiv/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_1e-05/model/model.safetensors b/gpt2-medium/ArXiv/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b66d564f3e374b9813bc7aa74a98a84a6782b2f --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e23129d348e78e1f8f53d20ca7a46a46d9b4dcd5fbca4d0a0263c905a152add5 +size 1419322880 diff --git a/gpt2-medium/ArXiv/lambda_2.0/model/config.json b/gpt2-medium/ArXiv/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/ArXiv/lambda_2.0/model/generation_config.json b/gpt2-medium/ArXiv/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/ArXiv/lambda_2.0/model/model.safetensors b/gpt2-medium/ArXiv/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..19cf1f61e4e974dff473628c0e7d916efb8883d2 --- /dev/null +++ b/gpt2-medium/ArXiv/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:def62c0e3ef59db3cae03456041ccdbec7be365aa5bb33f2bf7f15d5f9f4290e +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_0.0/model/config.json b/gpt2-medium/DM Mathematics/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.0/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.0/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..520587911efc7b7b3871a00813f6ce9df8067392 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77c47fd96479bb5b51b205d13301ad05ebfd7277b656ec4340f7b6a3ed2eb56 +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_0.0001/model/config.json b/gpt2-medium/DM Mathematics/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.0001/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.0001/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b9a74a88d3bdf2acfed8a330efea6af6e2925c09 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:374bb37379303436e87351057457f2b6c538fb7e56afdb498163332a23bac5c5 +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_0.001/model/config.json b/gpt2-medium/DM Mathematics/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.001/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.001/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b74b0817e062d10e007eac9f9ef5d999077debb --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bbe8e4698aef04c0198462bc0df818a1273cc2f9724c2790dd14895e3b5937b +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_0.01/model/config.json b/gpt2-medium/DM Mathematics/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.01/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.01/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f152cd4d258fbaa9ca306934dd4e38a278874b3d --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a070d63eedfd00e2ad74796c789d5b3e7125fcdb909ba8d67312bc5cf84d22fb +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_0.1/model/config.json b/gpt2-medium/DM Mathematics/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.1/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.1/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..eb377b53a5f747512adc811566bf2ae72ca1fe4a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:783d7bd4292a38caa267a4db941234d24fd0d673ecfba304e3b35af5391cadd6 +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_0.3/model/config.json b/gpt2-medium/DM Mathematics/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.3/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.3/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b594d391afd81997c117862509af856d116daad3 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd26f8b1e6c03f14fd9c391ced762f088f055f4ec518f649673b5b5326c495be +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_0.5/model/config.json b/gpt2-medium/DM Mathematics/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.5/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_0.5/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f32997c923c02c6f6ae265e38845fa2ac98f957c --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e92120fb64a27f0b2f341b11c042e0907f3116e91e464e4e47f6106b960c7ff +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_1.0/model/config.json b/gpt2-medium/DM Mathematics/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_1.0/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_1.0/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b6146b07b3a786d7bf0a41fc58a8933f8a933fef --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99c7c96d19c6262479fb7c291063cbc3afece274dd3546c3ede495422ac13a9f +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_1e-05/model/config.json b/gpt2-medium/DM Mathematics/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_1e-05/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_1e-05/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..13bc37e999bf57169f3f28f4f6bf4370186fa120 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9065a14328693c7578944a64c478c861ce71c518ebebfb686de0fc8ea8f46d +size 1419322880 diff --git a/gpt2-medium/DM Mathematics/lambda_2.0/model/config.json b/gpt2-medium/DM Mathematics/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/DM Mathematics/lambda_2.0/model/generation_config.json b/gpt2-medium/DM Mathematics/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/DM Mathematics/lambda_2.0/model/model.safetensors b/gpt2-medium/DM Mathematics/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6289d426d13df154912eef3fc7adc6fb136d1dec --- /dev/null +++ b/gpt2-medium/DM Mathematics/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:504fb6cb2cf32f361669cae059148964767fa77a833a52779e555c708fb54306 +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_0.0/model/config.json b/gpt2-medium/EuroParl/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_0.0/model/generation_config.json b/gpt2-medium/EuroParl/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_0.0/model/model.safetensors b/gpt2-medium/EuroParl/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c78e1ad718f516f291a1107f44e09f21ca0b8a8 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52542066c8033aa7ff833e3266a16282548e2b3efed9bacfc61715917a76860f +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_0.0001/model/config.json b/gpt2-medium/EuroParl/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_0.0001/model/generation_config.json b/gpt2-medium/EuroParl/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_0.0001/model/model.safetensors b/gpt2-medium/EuroParl/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7ef65eacfcf1bb88c4a6cb4db5b36131fb286643 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cd3fe9b128f39f2a97861ebbf74a3bd8e28293f338eb7936d774dc5312f1153 +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_0.001/model/config.json b/gpt2-medium/EuroParl/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_0.001/model/generation_config.json b/gpt2-medium/EuroParl/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_0.001/model/model.safetensors b/gpt2-medium/EuroParl/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..272e96bcd7f1e4ff9779bce2c3ea4de1005c7dd9 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ccee5b0c1aad63b8f606f29c557aa60708584e496d559413da03377558ddd6b +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_0.01/model/config.json b/gpt2-medium/EuroParl/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_0.01/model/generation_config.json b/gpt2-medium/EuroParl/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_0.01/model/model.safetensors b/gpt2-medium/EuroParl/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2ec998999e3e3b337d8228847d635ecaad298ab --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ebf42613cfbca0ee13d5cee1223112e0811a52829c5170f4d1517fe45813f84 +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_0.1/model/config.json b/gpt2-medium/EuroParl/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_0.1/model/generation_config.json b/gpt2-medium/EuroParl/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_0.1/model/model.safetensors b/gpt2-medium/EuroParl/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c8ee523b5a0c381df6743428ee810bdda056a348 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7244cfdc993bfcb10755eef40aeda470f5b0d916b534c331863667292f57c015 +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_0.3/model/config.json b/gpt2-medium/EuroParl/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_0.3/model/generation_config.json b/gpt2-medium/EuroParl/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_0.3/model/model.safetensors b/gpt2-medium/EuroParl/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0a26a15626bcb37b7aa00cdcf86692ab5a3f2b5 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e3079efbb0e00dee8526d06cb49be97520b75938b3e8ed5295d3576281d442d +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_0.5/model/config.json b/gpt2-medium/EuroParl/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_0.5/model/generation_config.json b/gpt2-medium/EuroParl/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_0.5/model/model.safetensors b/gpt2-medium/EuroParl/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e483ef986f6518dd2b223a9f8d45afc9c9645d8 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04975895c4527cba405c733ec30adb2c05b8e54aea0e032d09133ca8f37d3b82 +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_1.0/model/config.json b/gpt2-medium/EuroParl/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_1.0/model/generation_config.json b/gpt2-medium/EuroParl/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_1.0/model/model.safetensors b/gpt2-medium/EuroParl/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..299637fcfc7f1b0af8d714e5824d92c676bfe3be --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:202c21a1814ca8bd995fe545d31c98076e65f2b94ee04f9c31ceb8006253dbec +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_1e-05/model/config.json b/gpt2-medium/EuroParl/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_1e-05/model/generation_config.json b/gpt2-medium/EuroParl/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_1e-05/model/model.safetensors b/gpt2-medium/EuroParl/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c4cd0874244fbfb0fb36ca05a3e7d593f145698c --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccbf0e563bdc7b2a5907734aaad03dd891b81fcc40caa8a403470e484f83b7f6 +size 1419322880 diff --git a/gpt2-medium/EuroParl/lambda_2.0/model/config.json b/gpt2-medium/EuroParl/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/EuroParl/lambda_2.0/model/generation_config.json b/gpt2-medium/EuroParl/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/EuroParl/lambda_2.0/model/model.safetensors b/gpt2-medium/EuroParl/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..47b768e489617059a38d7b2801f0ee0d364d6303 --- /dev/null +++ b/gpt2-medium/EuroParl/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdbccfba629da84c8fe3700f8155b773a6a214239810b969df2c636af160164a +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_0.0/model/config.json b/gpt2-medium/FreeLaw/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_0.0/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_0.0/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f3f2ead5ac149d5881c86e4fb37b08f4a5dad403 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4b42f8f6b42103e7253b8adcc7aa33cad2cea5e4ad7719e152f23355fbb989 +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_0.0001/model/config.json b/gpt2-medium/FreeLaw/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_0.0001/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_0.0001/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a8f080e9f38536e56105b9435efdbf4950b808f --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f588ff95c2972e8637c7ee5090dab8ecff2eebd779d6b8ef7483e8fa29aa89b +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_0.001/model/config.json b/gpt2-medium/FreeLaw/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_0.001/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_0.001/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3023579b839b5d73854f0d6e197265f18433dcca --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d0216e1935acaf2cb434e1c4a6d5b662c03cce08225d3a761e52f02bc41657 +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_0.01/model/config.json b/gpt2-medium/FreeLaw/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_0.01/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_0.01/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87f15c435e4590f9a662f70b1ba37beda6d792e0 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ea51b9d0aec768d3a6c879a30575e4c31f04e1e65581b1e866a53a26cc36743 +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_0.1/model/config.json b/gpt2-medium/FreeLaw/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_0.1/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_0.1/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b1ec09d0afc50cabc3b22beed1e793adb8efcc3 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a6836c9a9bbdd77eeff2484f77087c77b3d5b33805dc0cd2712fb6af5278f4 +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_0.3/model/config.json b/gpt2-medium/FreeLaw/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_0.3/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_0.3/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cde2af67fdd8f38b01ec1c90d77f4acef5ca0165 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:501479ce7130e8b0eb919a5198583d7c980b7c2ed842831e5dd9ad4a780cb7de +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_0.5/model/config.json b/gpt2-medium/FreeLaw/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_0.5/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_0.5/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d07e906af13466dfffb580187b6a92ef60a1887 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7646fa93b34a09472c720e50b8e5863a7ca335fd043b40ecfa30227669d5f031 +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_1.0/model/config.json b/gpt2-medium/FreeLaw/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_1.0/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_1.0/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92a1ab91b2c786189ddcc1bb8e146b7f3f18a43a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6da025219e65678a951bbc6bd87a632ac720a948e952fcb44680f578bac40e5 +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_1e-05/model/config.json b/gpt2-medium/FreeLaw/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_1e-05/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_1e-05/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..22b4c9d0fc8e84e26ca74aab20310d807e8af7bb --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:629c0315125f5655d378f40bf3aacbbe062dbf58dc5c47dca2f639b58fb4ae18 +size 1419322880 diff --git a/gpt2-medium/FreeLaw/lambda_2.0/model/config.json b/gpt2-medium/FreeLaw/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/FreeLaw/lambda_2.0/model/generation_config.json b/gpt2-medium/FreeLaw/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/FreeLaw/lambda_2.0/model/model.safetensors b/gpt2-medium/FreeLaw/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..006a2189c2c567cc2e14c1dee00eb697b0cc8088 --- /dev/null +++ b/gpt2-medium/FreeLaw/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a890ed5f11751a5700d39beedadddc47d9baef3e255169e6fcd0748a1d573818 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_0.0/model/config.json b/gpt2-medium/Github/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_0.0/model/generation_config.json b/gpt2-medium/Github/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_0.0/model/model.safetensors b/gpt2-medium/Github/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11ec5f695ddd14480b24f61e853033d9e5811d5e --- /dev/null +++ b/gpt2-medium/Github/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd7f4851378289b7869ad91e3f6726d3c6b9cf4a492415012bb8ad2b9534dc80 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_0.0001/model/config.json b/gpt2-medium/Github/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_0.0001/model/generation_config.json b/gpt2-medium/Github/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_0.0001/model/model.safetensors b/gpt2-medium/Github/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f26b0bc1e9eae37f84cf6dd6000efa17d3850fa --- /dev/null +++ b/gpt2-medium/Github/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed244a651bb5f1fc0a17fa1c2cf067e2b1f8062372cf6f9d8f36b209838507a +size 1419322880 diff --git a/gpt2-medium/Github/lambda_0.001/model/config.json b/gpt2-medium/Github/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_0.001/model/generation_config.json b/gpt2-medium/Github/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_0.001/model/model.safetensors b/gpt2-medium/Github/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c467057549680ce8f57a17a507b9afdeec7b7304 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10a1f3b0238d94115536fdd82792839db9fb887c59301f718e3a1055dd81d4c8 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_0.01/model/config.json b/gpt2-medium/Github/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_0.01/model/generation_config.json b/gpt2-medium/Github/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_0.01/model/model.safetensors b/gpt2-medium/Github/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e43c8dc6d20e424872bf1a27168b48e18c922037 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f692ec912a36dd882884dbcf51e92b82c1ce424cf2635ad75abf1321ee1490e0 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_0.1/model/config.json b/gpt2-medium/Github/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_0.1/model/generation_config.json b/gpt2-medium/Github/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_0.1/model/model.safetensors b/gpt2-medium/Github/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a222af9801f8a64d8819c9110d3338a2d2d5db8b --- /dev/null +++ b/gpt2-medium/Github/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fee20ff2a8dc8f619bb4361e0f40a5c75f962a1015463fefd429ae64a62e4a14 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_0.3/model/config.json b/gpt2-medium/Github/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_0.3/model/generation_config.json b/gpt2-medium/Github/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_0.3/model/model.safetensors b/gpt2-medium/Github/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..696320c15eabde3c0ebdafbe2ed0ff2803857f10 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:558158a813166495cf1354ac910b2f08831e5707005507eba5a6b9c57a001bd1 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_0.5/model/config.json b/gpt2-medium/Github/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_0.5/model/generation_config.json b/gpt2-medium/Github/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_0.5/model/model.safetensors b/gpt2-medium/Github/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b30b79df4ad49eea0daa9571b35ce59286538f3a --- /dev/null +++ b/gpt2-medium/Github/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:297d562942371ae514cdf67464335fa00e8e5d768724838c680089fa4681656e +size 1419322880 diff --git a/gpt2-medium/Github/lambda_1.0/model/config.json b/gpt2-medium/Github/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_1.0/model/generation_config.json b/gpt2-medium/Github/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_1.0/model/model.safetensors b/gpt2-medium/Github/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c45974ca15c4c227a0d65f14715af6eeb25f5752 --- /dev/null +++ b/gpt2-medium/Github/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d54d23f79939c50419b07b5698c9e80e0f112ee54f859a499bd3c76f7e3a2587 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_1e-05/model/config.json b/gpt2-medium/Github/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_1e-05/model/generation_config.json b/gpt2-medium/Github/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_1e-05/model/model.safetensors b/gpt2-medium/Github/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..641ef6f49e59af4468db6ad530b9ca356f541a6f --- /dev/null +++ b/gpt2-medium/Github/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cd49be56147ca5fee8b05cbfef40e94d97c48ac3fad03d661f9cd70cbad2a62 +size 1419322880 diff --git a/gpt2-medium/Github/lambda_2.0/model/config.json b/gpt2-medium/Github/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Github/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Github/lambda_2.0/model/generation_config.json b/gpt2-medium/Github/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Github/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Github/lambda_2.0/model/model.safetensors b/gpt2-medium/Github/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e3842f3daf10d6472716f0533c92f156bbbe8b57 --- /dev/null +++ b/gpt2-medium/Github/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b0c4a14564c58b1be553de53d5258506be8c4f82bb0389d162a1a51ce6cc471 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e5f5a77a6ce66bfabadbd48e29af49adceb8fef --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:496470c6b7c29e890f909d49cd8de157109ef3075f0c17f39a389a2d42572990 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..576340bce5100283b1b409babb6fceef93f5a447 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02bc7992b65088718f5e2fdef48d30559977e8d742f4895df0040da7a56def48 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..db8d6ff9a2ff1e55435b821a877e589c32be7aee --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:683ace261de4522525d73ed90b40e821b6a564a906f05bab02df0b331dca53dd +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a5c9bacefc65622adcd322390862efa94d14aab6 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc5ab2483fd2d22a78927b06873c1ea7e7c91b02c61a2ee26c413c692babd04 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4e6c9461da58c51854fd2027cdb16caebf3d3408 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a799be5324f0ab955b5c511d31c10ac0f77f78d0eadac45805b466bf87859467 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..994e0609d3bbf3722dcc27257bfff85192742560 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd0b6a2eac30ec2f8ee6331c194f98d10745b40c233fbb7b6445df3630dd9ad +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5fe36c8fb866b8c1d0b0058f577fb60ef1b0f7ff --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7511796ccd36eee6843db4d0b2356028ea9c218dc4863ac418169768053a06f3 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cabd589ea8d983303cb4cd7fec4fde0298760797 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ecf54e05cdd8670d1ee41e5530651dc7ab13560380f02dd394d4f0ca9506442 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6025632d4cf9d1afda161c331dc8c750f9ae3244 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aef2eb0532558ea202c99e90b8dcdc0414cd2fee1544fbe0f4b3e3574b284c39 +size 1419322880 diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/generation_config.json b/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/model.safetensors b/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..54350d34f7f63a3f42ec42ae961b97b151965440 --- /dev/null +++ b/gpt2-medium/Gutenberg (PG-19)/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49e95a9ed59ea5c4e15ec41c55987c538d8f46d2b5e3cacf75e06c082fb58e6e +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_0.0/model/config.json b/gpt2-medium/OpenWebText2/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.0/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.0/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..afd1cc20286d9d1d9d14f69b50eaf7fe77a38c09 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ec16ce9efc10cbc2fd1ad8742f3d835fdcee6a7bfb39b6497e58bd5d5ebe646 +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_0.0001/model/config.json b/gpt2-medium/OpenWebText2/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.0001/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.0001/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3f8fe811dbbdcce6ecba1fd02ab4440b7d7bba88 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe618951779fbc277636e4dc85b0d155ecba5caa379545c30b558c1d33044f96 +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_0.001/model/config.json b/gpt2-medium/OpenWebText2/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.001/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.001/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..380c2e6b1d86df6064f08e42680f79744b5de46a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b428d7f1492fcc7b6e88618d6c1785218dff970d3ede1d7d4eccb91b58c8fafd +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_0.01/model/config.json b/gpt2-medium/OpenWebText2/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.01/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.01/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..555f0a6a454e23e09b99f6987426c75fd0f22e4a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:442c4ec22ef87fc26db97e027e28d6dfe1058805aa8e96ff797f428b87f1f5cb +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_0.1/model/config.json b/gpt2-medium/OpenWebText2/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.1/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.1/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f6da5b9dc257fb87602e3b41fae07276bb51563f --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c103fa22553f50870714afb6d60e0422c731fe9b8c7d62f30104a06f60626daa +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_0.3/model/config.json b/gpt2-medium/OpenWebText2/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.3/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.3/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..623c52d5f70f9fa3c9d02490fca446da16198f4c --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:270384c0b6eef34c9889606d81ab18af4c890f9e1f1958dff0dc6d2342ab2c14 +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_0.5/model/config.json b/gpt2-medium/OpenWebText2/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.5/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_0.5/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de4c7c06fdbf6f9f765cb98807f819c894ca5422 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76e42f9ebfd096f95ca80b769f631a2ddd96591d1ba984957dc92f09ce11f6be +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_1.0/model/config.json b/gpt2-medium/OpenWebText2/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_1.0/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_1.0/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a08a9dec5a0161e7ebf0a98a71b2a79ca69f971f --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe4aae085be831a6714d10d161d206c96428410750b613c9758e919cf9ee721 +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_1e-05/model/config.json b/gpt2-medium/OpenWebText2/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_1e-05/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_1e-05/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..666c16d3e9aa4add0a3f01220e44815eae5d70d9 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3975dcdb61db3971e70feca2c9574a8ee2c4b4e7d26284d83a5652ace850e8fe +size 1419322880 diff --git a/gpt2-medium/OpenWebText2/lambda_2.0/model/config.json b/gpt2-medium/OpenWebText2/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/OpenWebText2/lambda_2.0/model/generation_config.json b/gpt2-medium/OpenWebText2/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/OpenWebText2/lambda_2.0/model/model.safetensors b/gpt2-medium/OpenWebText2/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2f1c989e8c167438c4fc3e38053fa12e1f84ce45 --- /dev/null +++ b/gpt2-medium/OpenWebText2/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b525781a7b8bf45e5852dac56d38e205c0c147f80a8a4b48ab105b9bf98f9d +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.0/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.0/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.0/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c97b3d30a664ea64d82e73384a1b6e41e4cd1eda --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd833000d788053d4cfb8d326d1a8990a10701a477ad58c5f76ca4de881a4974 +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8b02655615cf874509866d753ff865d89b6e2d3b --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5714da6d27480eb537f2450de121575561f007a81e1f3e710e0521b42c8a09bf +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.001/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.001/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.001/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a7391e5f7b348eb8542bd2b00ed7d0c73d088a81 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40413bdbf286ce75e522a140efd171d2d8047b83bdcfd2deb78888a194b1f74e +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.01/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.01/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.01/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9a826c099e6d877b48027cf28948e4fff5fc3148 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb57aac1d5953e7690845a6b133ac8757c572ebcb76a4cab890cb15040f0aefe +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.1/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.1/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.1/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8f5f36c38dbed2d4d2d09565171c552ec56abe4b --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a0cb574c2e2f0b952b88ac003adc8554281f1138e648cd8bb566a040acdfcdc +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.3/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.3/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.3/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7367ab4bea788107f0a011778a9e115a938fd164 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7070c7464c141c7eb4d8ed420e162d84457aab0b3ae115c12c18ba60ad0b347 +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.5/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.5/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_0.5/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ed13b94f076bbf5f2af744f42034b22eca244197 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cae9f002e7f3e76112bcda16e272eeadb4d35d56da0fcad40ffcf00f949db04 +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_1.0/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_1.0/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_1.0/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e56ad93011abec41c97be3f6ebc9ee3a62bb4ddc --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd4f3a2da72a1d1a19588df45ea59aa4145b804dc1e3926f56a4148f442e6b45 +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d2ef4a9d3503c8f99bfb573a5a276ad12a61094 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff5ff510a0a159108f993b73e81a5ba5eb2ab3f9a7c1023cdb59c351ac0254aa +size 1419322880 diff --git a/gpt2-medium/PubMed Abstracts/lambda_2.0/model/config.json b/gpt2-medium/PubMed Abstracts/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_2.0/model/generation_config.json b/gpt2-medium/PubMed Abstracts/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Abstracts/lambda_2.0/model/model.safetensors b/gpt2-medium/PubMed Abstracts/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f049fd1b4fae70d5e43d8799a24166a0638c27f5 --- /dev/null +++ b/gpt2-medium/PubMed Abstracts/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315144bd692a288de30413785520364738b9c067a60f3b906fb82161c7765361 +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_0.0/model/config.json b/gpt2-medium/PubMed Central/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_0.0/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_0.0/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..63e8fa8d34566f21e537cbac4c564b8c9efe5eb3 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e6ff431a34695ead41a5ab370eb82603489b468cdaa27dce61cd4a9e8ae3824 +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_0.0001/model/config.json b/gpt2-medium/PubMed Central/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_0.0001/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_0.0001/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64d8a395c01d819dde3430218e9dab836b930a16 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4061527ea3b8cce82d878d7aab278b09f0c4dda3093c2ec8dfca4f8eeddae385 +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_0.001/model/config.json b/gpt2-medium/PubMed Central/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_0.001/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_0.001/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..16e26c0446009a95e458eab175f5b0c4e4621733 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14d1dc2f6900c7a49a2c28e17e4aef93e2bbb2a286f75b3d1f9da08b7c3885ab +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_0.01/model/config.json b/gpt2-medium/PubMed Central/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_0.01/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_0.01/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4a81c6cb913db7f5a1dcf6542f306190940fe343 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37328b9fbf343238882b4aade7f3193060475254fac843d74b7f304dd5e44d6f +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_0.1/model/config.json b/gpt2-medium/PubMed Central/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_0.1/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_0.1/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0f3933028ae8dcc12886f85d2b5578c4377b97b4 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f22700324bdb03bbd97af51e8e7c2f271bdaed05e7079e1cabf78200de9ac6d9 +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_0.3/model/config.json b/gpt2-medium/PubMed Central/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_0.3/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_0.3/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b1beb2fc382c1a0f2db4099ec4993820428eba0a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b06731a27ce56fba0475a5b4993e12ca04130c478543863861c27168ebab5600 +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_0.5/model/config.json b/gpt2-medium/PubMed Central/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_0.5/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_0.5/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..86ca7ffcd248de29017207cfc790e7fc510f2ce5 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1be682409e10905e2836a45b01b5d0d4b7f2dcc95134d9e0c94c8c4b7894a9ec +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_1.0/model/config.json b/gpt2-medium/PubMed Central/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_1.0/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_1.0/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b941f0edd4ba4df512acb4a6b112e5aa65a98b72 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:026836d947ec172bb32549f37d633e6a448a78908fcadb0c1bd665af7d62594a +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_1e-05/model/config.json b/gpt2-medium/PubMed Central/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_1e-05/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_1e-05/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..59e52aa4bffa9e656bf108f01f81a90c2d435388 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:659621efd8665f31c9c6702a4a09670df7b3953794e2369bf055476f99b7c21d +size 1419322880 diff --git a/gpt2-medium/PubMed Central/lambda_2.0/model/config.json b/gpt2-medium/PubMed Central/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/PubMed Central/lambda_2.0/model/generation_config.json b/gpt2-medium/PubMed Central/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/PubMed Central/lambda_2.0/model/model.safetensors b/gpt2-medium/PubMed Central/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe4152691bbecee636b32671d281b24aa7ed4420 --- /dev/null +++ b/gpt2-medium/PubMed Central/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6dc63273be30ee1761903376d05f2b7592272efeaecca636945bc8ba14a40ed6 +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_0.0/model/config.json b/gpt2-medium/StackExchange/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_0.0/model/generation_config.json b/gpt2-medium/StackExchange/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_0.0/model/model.safetensors b/gpt2-medium/StackExchange/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e5dca5f9f8d3b4e1253830f91589456ce15201f3 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e9f9de37ca760e8474ba0a54e1cc4e4e4210e7f67d1f93469d84f3e483d874 +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_0.0001/model/config.json b/gpt2-medium/StackExchange/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_0.0001/model/generation_config.json b/gpt2-medium/StackExchange/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_0.0001/model/model.safetensors b/gpt2-medium/StackExchange/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5f09003c7a10e6825cbca0aae6e8bef7d985fc8c --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4f9232453b22bd71651df7eccfd7aad6c81ef41cdae69a3acdec602b456b099 +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_0.001/model/config.json b/gpt2-medium/StackExchange/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_0.001/model/generation_config.json b/gpt2-medium/StackExchange/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_0.001/model/model.safetensors b/gpt2-medium/StackExchange/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e1049d503f8529144ddccfc502ccae5857572061 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b85f0a8aa34ea23afdb79450fb9030565956560b6ade9ef0c23641907eed2a7c +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_0.01/model/config.json b/gpt2-medium/StackExchange/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_0.01/model/generation_config.json b/gpt2-medium/StackExchange/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_0.01/model/model.safetensors b/gpt2-medium/StackExchange/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4d3d6ee939ac5780480f2da9a411cf1115361f2e --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:128fb53f810012053623fd287177c91728347eb1012bcd38223ddaf5e70b1dff +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_0.1/model/config.json b/gpt2-medium/StackExchange/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_0.1/model/generation_config.json b/gpt2-medium/StackExchange/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_0.1/model/model.safetensors b/gpt2-medium/StackExchange/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3b7325448175086c7dfa9bd817d4969e657e2fea --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:759a2e7008e0ea7186783f887a235f306ff60849dd97470470bf9ff28ee0a317 +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_0.3/model/config.json b/gpt2-medium/StackExchange/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_0.3/model/generation_config.json b/gpt2-medium/StackExchange/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_0.3/model/model.safetensors b/gpt2-medium/StackExchange/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fd2c17b45de978418aa581d2e1bba4a41227b2b2 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c1e3f519a559565430019437a93aa37af54d41c89766cb6001300ad2ce81af9 +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_0.5/model/config.json b/gpt2-medium/StackExchange/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_0.5/model/generation_config.json b/gpt2-medium/StackExchange/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_0.5/model/model.safetensors b/gpt2-medium/StackExchange/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc2872510811cfb9a076f9e3613cc10a48c70546 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:becb5b24ed0d95298e0f9468307893e2b4e8dfc67a41de2b17dfeafe0a99a418 +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_1.0/model/config.json b/gpt2-medium/StackExchange/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_1.0/model/generation_config.json b/gpt2-medium/StackExchange/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_1.0/model/model.safetensors b/gpt2-medium/StackExchange/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..08cfd4d674cf7df49af620e58f5a764da1bb1c95 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c03ee150aeba74eebdcbeb9fc4f8f651106414ac499b7dc0819b21ae232fafd2 +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_1e-05/model/config.json b/gpt2-medium/StackExchange/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_1e-05/model/generation_config.json b/gpt2-medium/StackExchange/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_1e-05/model/model.safetensors b/gpt2-medium/StackExchange/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0aab00cfe6627c8805dfc1045f2e6f72ad2d6582 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e910b882905f70137351b14ef0d38659501e288c6dcfca4eee89084c9593a1b +size 1419322880 diff --git a/gpt2-medium/StackExchange/lambda_2.0/model/config.json b/gpt2-medium/StackExchange/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/StackExchange/lambda_2.0/model/generation_config.json b/gpt2-medium/StackExchange/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/StackExchange/lambda_2.0/model/model.safetensors b/gpt2-medium/StackExchange/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3654db2f4f3ab2df94e010d1f2252b4d7dbb81bb --- /dev/null +++ b/gpt2-medium/StackExchange/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce86642ef15ef2b8a782a986c4430ab9fd574137e7fa56ae171545832f10fed0 +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.0/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_0.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.0/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_0.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.0/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_0.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..904ee365b086f44a64a7a6f4b45682a87d583520 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef31ba05c2c7d507303d6a3016f62cc0a97d23bd59301d73714b5be90d86c56b +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..96f58ecfc777d8f39854a08736692ce18e05ca45 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.0001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba749b5dfef31a9105d1f02faff54e2c251b78dbdf85ba430dc68c791bbbf47 +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.001/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_0.001/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.001/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.001/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_0.001/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.001/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.001/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_0.001/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe70535fa0f40a1c0812865e3aacf5f1a6c6d951 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.001/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8ff441e6b64be4a0b55c96763b86d4c42786eade303d499fcdaf03609a886f5 +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.01/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_0.01/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.01/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.01/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_0.01/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.01/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.01/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_0.01/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d324fdae53f2ce46f273e1bde4977ad578e2067 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.01/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ebcbbb6c2f5d1ec40546b9ce69f6a3f3f51b85b5c31e801b314b13c9d621da4e +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.1/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_0.1/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.1/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.1/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_0.1/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.1/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.1/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_0.1/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2e0ef01373fe9bd6401bfd864dca81fcf9859c04 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.1/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ec983670861ac75dc2db74b7a1970490659a680e45b5e54a0fcf4c8f799d5a2 +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.3/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_0.3/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.3/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.3/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_0.3/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.3/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.3/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_0.3/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2bf6f6f4e01eb8d9ef51273ce7a922ebb355826e --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.3/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7083dbedf6738438a997e93f6f26349bc09e1dfd2c270f45aa52cdecf3d74758 +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.5/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_0.5/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.5/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.5/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_0.5/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.5/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_0.5/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_0.5/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f9338c7807362ac1f6a87d2e4c5947186620aed8 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_0.5/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97a22f37e52c9f3eca72624ed11248d88c3841c2625cd4b7745b6ab9a7edfccc +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_1.0/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_1.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_1.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_1.0/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_1.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_1.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_1.0/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_1.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7c0e101c83dfd7b2ca36f708a7a9e26c4ae28951 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_1.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:004c7fee281eb5d371cd83b559fb20dcc37d2e894f84fe76eaf1c582678dc51d +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9509a6c50ca87135d2e05946cdae951499c75981 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_1e-05/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8259f238251055b2dc4dd85e52d288c0b492f9d18521e5bce0644bf1d1a1fd8 +size 1419322880 diff --git a/gpt2-medium/Wikipedia (en)/lambda_2.0/model/config.json b/gpt2-medium/Wikipedia (en)/lambda_2.0/model/config.json new file mode 100644 index 0000000000000000000000000000000000000000..806965eb21024bb7da7c1dc3ccf5f570a059f31a --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_2.0/model/config.json @@ -0,0 +1,43 @@ +{ + "activation_function": "gelu_new", + "add_cross_attention": false, + "architectures": [ + "GPT2LMHeadModel" + ], + "attn_pdrop": 0.1, + "bos_token_id": 50256, + "dtype": "float32", + "embd_pdrop": 0.1, + "eos_token_id": 50256, + "initializer_range": 0.02, + "layer_norm_epsilon": 1e-05, + "model_type": "gpt2", + "n_ctx": 1024, + "n_embd": 1024, + "n_head": 16, + "n_inner": null, + "n_layer": 24, + "n_positions": 1024, + "n_special": 0, + "pad_token_id": null, + "predict_special_tokens": true, + "reorder_and_upcast_attn": false, + "resid_pdrop": 0.1, + "scale_attn_by_inverse_layer_idx": false, + "scale_attn_weights": true, + "summary_activation": null, + "summary_first_dropout": 0.1, + "summary_proj_to_labels": true, + "summary_type": "cls_index", + "summary_use_proj": true, + "task_specific_params": { + "text-generation": { + "do_sample": true, + "max_length": 50 + } + }, + "tie_word_embeddings": true, + "transformers_version": "5.14.1", + "use_cache": true, + "vocab_size": 50257 +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_2.0/model/generation_config.json b/gpt2-medium/Wikipedia (en)/lambda_2.0/model/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..d1aada487d80e4283d678bf4968cf5f6533ccd15 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_2.0/model/generation_config.json @@ -0,0 +1,6 @@ +{ + "_from_model_config": true, + "bos_token_id": 50256, + "eos_token_id": 50256, + "transformers_version": "5.14.1" +} diff --git a/gpt2-medium/Wikipedia (en)/lambda_2.0/model/model.safetensors b/gpt2-medium/Wikipedia (en)/lambda_2.0/model/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8802a580a9ff40491abb8c377f9b26343ee476a8 --- /dev/null +++ b/gpt2-medium/Wikipedia (en)/lambda_2.0/model/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:510e0a6f0a91917eb6a552edd2fb7bf8f76e7dbb4a72d4cac94871b05d84ed4b +size 1419322880