| { | |
| "model_type": "gpt2", | |
| "architectures": ["GPT2LMHeadModel"], | |
| "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, | |
| "bos_token_id": 50256, | |
| "eos_token_id": 50256, | |
| "pad_token_id": 50256, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 512, | |
| "temperature": 0.8, | |
| "top_p": 0.95, | |
| "top_k": 50 | |
| } | |
| }, | |
| "use_cache": true, | |
| "summary": "ChatGPT-style conversational model fine-tuned from GPT-2 for dialogue and instruction-following." | |
| } | |