Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- gpt2-medium/ArXiv/lambda_0.0/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_0.0/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_0.0/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_0.0001/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_0.0001/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_0.0001/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_0.001/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_0.001/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_0.001/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_0.01/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_0.01/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_0.01/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_0.1/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_0.1/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_0.1/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_0.3/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_0.3/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_0.3/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_0.5/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_0.5/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_0.5/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_1.0/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_1.0/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_1.0/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_1e-05/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_1e-05/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_1e-05/model/model.safetensors +3 -0
- gpt2-medium/ArXiv/lambda_2.0/model/config.json +43 -0
- gpt2-medium/ArXiv/lambda_2.0/model/generation_config.json +6 -0
- gpt2-medium/ArXiv/lambda_2.0/model/model.safetensors +3 -0
- gpt2-medium/DM Mathematics/lambda_0.0/model/config.json +43 -0
- gpt2-medium/DM Mathematics/lambda_0.0/model/generation_config.json +6 -0
- gpt2-medium/DM Mathematics/lambda_0.0/model/model.safetensors +3 -0
- gpt2-medium/DM Mathematics/lambda_0.0001/model/config.json +43 -0
- gpt2-medium/DM Mathematics/lambda_0.0001/model/generation_config.json +6 -0
- gpt2-medium/DM Mathematics/lambda_0.0001/model/model.safetensors +3 -0
- gpt2-medium/DM Mathematics/lambda_0.001/model/config.json +43 -0
- gpt2-medium/DM Mathematics/lambda_0.001/model/generation_config.json +6 -0
- gpt2-medium/DM Mathematics/lambda_0.001/model/model.safetensors +3 -0
- gpt2-medium/DM Mathematics/lambda_0.01/model/config.json +43 -0
- gpt2-medium/DM Mathematics/lambda_0.01/model/generation_config.json +6 -0
- gpt2-medium/DM Mathematics/lambda_0.01/model/model.safetensors +3 -0
- gpt2-medium/DM Mathematics/lambda_0.1/model/config.json +43 -0
- gpt2-medium/DM Mathematics/lambda_0.1/model/generation_config.json +6 -0
- gpt2-medium/DM Mathematics/lambda_0.1/model/model.safetensors +3 -0
- gpt2-medium/DM Mathematics/lambda_0.3/model/config.json +43 -0
- gpt2-medium/DM Mathematics/lambda_0.3/model/generation_config.json +6 -0
- gpt2-medium/DM Mathematics/lambda_0.3/model/model.safetensors +3 -0
- gpt2-medium/DM Mathematics/lambda_0.5/model/config.json +43 -0
- gpt2-medium/DM Mathematics/lambda_0.5/model/generation_config.json +6 -0
gpt2-medium/ArXiv/lambda_0.0/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_0.0/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_0.0/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe7d947c4c64bf94998caf627bf57e33ce7ffe6a783dbba6e402d44ffd3ca79e
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_0.0001/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_0.0001/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_0.0001/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b00c3bb5925d8b85bc5f2f8ee7952ec709848dcc80411078fc8f1a089311fcf6
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_0.001/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_0.001/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_0.001/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a556fab74c38856df6f580c28f0b3db72b78efcfffe56c542bc42fc8dfcfe489
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_0.01/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_0.01/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_0.01/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65c2214e9265290603191e5d4b21cf6b939b93a85c2c7019988a8e189f7bc4a1
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_0.1/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_0.1/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_0.1/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:75d40a78594380efbe481c9a249bcec2bdcf2bd8991ef05d78bcbe31b74b7604
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_0.3/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_0.3/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_0.3/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72c70dbd2877a6d29a31e1103b7754dc32de5081153275e81d9a77b3853d9b74
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_0.5/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_0.5/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_0.5/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6332e997971a42886df87a0b913a2bcbe8d8b51b47613adf15ea4a7256be470a
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_1.0/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_1.0/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_1.0/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed1d52eef4833891da2b4ef114bb82e4299b074be23a6b88e3dc345406cb5649
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_1e-05/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_1e-05/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_1e-05/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e23129d348e78e1f8f53d20ca7a46a46d9b4dcd5fbca4d0a0263c905a152add5
|
| 3 |
+
size 1419322880
|
gpt2-medium/ArXiv/lambda_2.0/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/ArXiv/lambda_2.0/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/ArXiv/lambda_2.0/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:def62c0e3ef59db3cae03456041ccdbec7be365aa5bb33f2bf7f15d5f9f4290e
|
| 3 |
+
size 1419322880
|
gpt2-medium/DM Mathematics/lambda_0.0/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.0/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.0/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f77c47fd96479bb5b51b205d13301ad05ebfd7277b656ec4340f7b6a3ed2eb56
|
| 3 |
+
size 1419322880
|
gpt2-medium/DM Mathematics/lambda_0.0001/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.0001/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.0001/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:374bb37379303436e87351057457f2b6c538fb7e56afdb498163332a23bac5c5
|
| 3 |
+
size 1419322880
|
gpt2-medium/DM Mathematics/lambda_0.001/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.001/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.001/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bbe8e4698aef04c0198462bc0df818a1273cc2f9724c2790dd14895e3b5937b
|
| 3 |
+
size 1419322880
|
gpt2-medium/DM Mathematics/lambda_0.01/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.01/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.01/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a070d63eedfd00e2ad74796c789d5b3e7125fcdb909ba8d67312bc5cf84d22fb
|
| 3 |
+
size 1419322880
|
gpt2-medium/DM Mathematics/lambda_0.1/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.1/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.1/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:783d7bd4292a38caa267a4db941234d24fd0d673ecfba304e3b35af5391cadd6
|
| 3 |
+
size 1419322880
|
gpt2-medium/DM Mathematics/lambda_0.3/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.3/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.3/model/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd26f8b1e6c03f14fd9c391ced762f088f055f4ec518f649673b5b5326c495be
|
| 3 |
+
size 1419322880
|
gpt2-medium/DM Mathematics/lambda_0.5/model/config.json
ADDED
|
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_function": "gelu_new",
|
| 3 |
+
"add_cross_attention": false,
|
| 4 |
+
"architectures": [
|
| 5 |
+
"GPT2LMHeadModel"
|
| 6 |
+
],
|
| 7 |
+
"attn_pdrop": 0.1,
|
| 8 |
+
"bos_token_id": 50256,
|
| 9 |
+
"dtype": "float32",
|
| 10 |
+
"embd_pdrop": 0.1,
|
| 11 |
+
"eos_token_id": 50256,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"layer_norm_epsilon": 1e-05,
|
| 14 |
+
"model_type": "gpt2",
|
| 15 |
+
"n_ctx": 1024,
|
| 16 |
+
"n_embd": 1024,
|
| 17 |
+
"n_head": 16,
|
| 18 |
+
"n_inner": null,
|
| 19 |
+
"n_layer": 24,
|
| 20 |
+
"n_positions": 1024,
|
| 21 |
+
"n_special": 0,
|
| 22 |
+
"pad_token_id": null,
|
| 23 |
+
"predict_special_tokens": true,
|
| 24 |
+
"reorder_and_upcast_attn": false,
|
| 25 |
+
"resid_pdrop": 0.1,
|
| 26 |
+
"scale_attn_by_inverse_layer_idx": false,
|
| 27 |
+
"scale_attn_weights": true,
|
| 28 |
+
"summary_activation": null,
|
| 29 |
+
"summary_first_dropout": 0.1,
|
| 30 |
+
"summary_proj_to_labels": true,
|
| 31 |
+
"summary_type": "cls_index",
|
| 32 |
+
"summary_use_proj": true,
|
| 33 |
+
"task_specific_params": {
|
| 34 |
+
"text-generation": {
|
| 35 |
+
"do_sample": true,
|
| 36 |
+
"max_length": 50
|
| 37 |
+
}
|
| 38 |
+
},
|
| 39 |
+
"tie_word_embeddings": true,
|
| 40 |
+
"transformers_version": "5.14.1",
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"vocab_size": 50257
|
| 43 |
+
}
|
gpt2-medium/DM Mathematics/lambda_0.5/model/generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 50256,
|
| 4 |
+
"eos_token_id": 50256,
|
| 5 |
+
"transformers_version": "5.14.1"
|
| 6 |
+
}
|