| { |
| "model_type": "gpt2", |
| "vocab_size": 50257, |
| "n_positions": 1024, |
| "n_ctx": 1024, |
| "n_embd": 768, |
| "n_layer": 12, |
| "n_head": 12, |
| "activation_function": "gelu_new", |
| "resid_pdrop": 0.1, |
| "embd_pdrop": 0.1, |
| "attn_pdrop": 0.1, |
| "layer_norm_epsilon": 1e-5, |
| "initializer_range": 0.02, |
| "summary_type": "cls_index", |
| "summary_use_proj": true, |
| "summary_activation": "tanh", |
| "summary_proj_to_labels": true, |
| "summary_first_dropout": 0.1, |
| "task_specific_params": { |
| "text-generation": { |
| "temperature": 0.7, |
| "top_p": 0.9, |
| "top_k": 50 |
| } |
| } |
| } |
|
|
