hf-tiny-model-private/tiny-random-GPT2LMHeadModel

1{2  "_name_or_path": "tiny_models/gpt2/GPT2LMHeadModel",3  "activation_function": "gelu",4  "architectures": [5    "GPT2LMHeadModel"6  ],7  "attn_pdrop": 0.1,8  "bos_token_id": 0,9  "embd_pdrop": 0.1,10  "eos_token_id": 0,11  "gradient_checkpointing": false,12  "initializer_range": 0.02,13  "is_decoder": true,14  "layer_norm_epsilon": 1e-05,15  "model_type": "gpt2",16  "n_embd": 32,17  "n_head": 4,18  "n_inner": 37,19  "n_layer": 5,20  "n_positions": 512,21  "pad_token_id": 1023,22  "reorder_and_upcast_attn": false,23  "resid_pdrop": 0.1,24  "scale_attn_by_inverse_layer_idx": false,25  "scale_attn_weights": true,26  "summary_activation": null,27  "summary_first_dropout": 0.1,28  "summary_proj_to_labels": true,29  "summary_type": "cls_index",30  "summary_use_proj": true,31  "torch_dtype": "float32",32  "transformers_version": "4.28.0.dev0",33  "type_vocab_size": 16,34  "use_cache": true,35  "vocab_size": 102436}37