krplt/GPT-Sponge

1{2  "_name_or_path": "EleutherAI/gpt-neo-1.3B",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    "global",22    "local",23    "global",24    "local",25    "global",26    "local",27    "global",28    "local",29    "global",30    "local",31    "global",32    "local"33  ],34  "attention_types": [35    [36      [37        "global",38        "local"39      ],40      1241    ]42  ],43  "bos_token_id": 50256,44  "embed_dropout": 0,45  "eos_token_id": 50257,46  "gradient_checkpointing": false,47  "hidden_size": 2048,48  "initializer_range": 0.02,49  "intermediate_size": null,50  "layer_norm_epsilon": 1e-05,51  "max_position_embeddings": 2048,52  "model_type": "gpt_neo",53  "num_heads": 16,54  "num_layers": 24,55  "pad_token_id": 50258,56  "resid_dropout": 0,57  "summary_activation": null,58  "summary_first_dropout": 0.1,59  "summary_proj_to_labels": true,60  "summary_type": "cls_index",61  "summary_use_proj": true,62  "task_specific_params": {63    "text-generation": {64      "do_sample": true,65      "max_length": 50,66      "temperature": 0.967    }68  },69  "tokenizer_class": "GPT2Tokenizer",70  "torch_dtype": "float32",71  "transformers_version": "4.20.0",72  "use_cache": true,73  "vocab_size": 50259,74  "window_size": 25675}76