| { |
| "_name_or_path": "Rschmaelzle/gpt_fol_full_v1", |
| "activation_function": "gelu_new", |
| "architectures": [ |
| "GPT2HeadWithValueModel" |
| ], |
| "attn_pdrop": 0.1, |
| "bos_token_id": 50256, |
| "embd_pdrop": 0.1, |
| "eos_token_id": 50256, |
| "gradient_checkpointing": false, |
| "id2label": { |
| "0": "LABEL_0" |
| }, |
| "initializer_range": 0.02, |
| "label2id": { |
| "LABEL_0": 0 |
| }, |
| "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, |
| "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 |
| } |
| }, |
| "torch_dtype": "float32", |
| "transformers_version": "4.3.2", |
| "use_cache": true, |
| "vocab_size": 50259 |
| } |
|
|
