| { | |
| "activation_function": "gelu", | |
| "architectures": [ | |
| "GPTNeoXForCausalLM" | |
| ], | |
| "attn_pdrop": 0.0, | |
| "bos_token_id": 2, | |
| "embd_pdrop": 0.0, | |
| "eos_token_id": 3, | |
| "gpt_j_residual": false, | |
| "gradient_checkpointing": false, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "lm_head_bias": false, | |
| "model_type": "gpt-neox", | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_inner": null, | |
| "n_layer": 12, | |
| "n_positions": 2048, | |
| "resid_pdrop": 0.0, | |
| "rotary": true, | |
| "rotary_dim": null, | |
| "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, | |
| "temperature": 1.0 | |
| } | |
| }, | |
| "tie_word_embeddings": false, | |
| "tokenizer_class": "T5Tokenizer", | |
| "torch_dtype": "float32", | |
| "use_cache": true, | |
| "vocab_size": 44416 | |
| } | |