| { | |
| "_name_or_path": "/proj/wara-ml/users/x_ariek/new_instruct/20b/hf/", | |
| "activation_function": "gelu", | |
| "apply_query_key_layer_scaling": true, | |
| "architectures": [ | |
| "GPT2LMHeadModel" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 2, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 3, | |
| "initializer_range": 0.008165, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_embd": 6144, | |
| "n_head": 48, | |
| "n_inner": 24576, | |
| "n_layer": 44, | |
| "n_positions": 2048, | |
| "normalize_attention_scores": true, | |
| "pad_token_id": 0, | |
| "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, | |
| "tokenizer_class": "GPTSw3Tokenizer", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.22.1", | |
| "use_cache": true, | |
| "vocab_size": 64000, | |
| "max_length": 2048 | |
| } | |