Jithendra-k/InterACT_micro

1{2  "_name_or_path": "EleutherAI/gpt-neo-125m",3  "activation_function": "gelu_new",4  "architectures": [5    "GPTNeoForCausalLM"6  ],7  "attention_dropout": 0,8  "attention_layers": [9    "global",10    "local",11    "global",12    "local",13    "global",14    "local",15    "global",16    "local",17    "global",18    "local",19    "global",20    "local"21  ],22  "attention_types": [23    [24      [25        "global",26        "local"27      ],28      629    ]30  ],31  "bos_token_id": 50256,32  "classifier_dropout": 0.1,33  "embed_dropout": 0,34  "eos_token_id": 50256,35  "gradient_checkpointing": false,36  "hidden_size": 768,37  "initializer_range": 0.02,38  "intermediate_size": null,39  "layer_norm_epsilon": 1e-05,40  "max_position_embeddings": 2048,41  "model_type": "gpt_neo",42  "num_heads": 12,43  "num_layers": 12,44  "resid_dropout": 0,45  "summary_activation": null,46  "summary_first_dropout": 0.1,47  "summary_proj_to_labels": true,48  "summary_type": "cls_index",49  "summary_use_proj": true,50  "torch_dtype": "float16",51  "transformers_version": "4.44.2",52  "use_cache": true,53  "vocab_size": 50257,54  "window_size": 25655}56