hf-tiny-model-private/tiny-random-GPT2Model
046
1{2 "_name_or_path": "tiny_models/gpt2/GPT2Model",3 "activation_function": "gelu",4 "architectures": [5 "GPT2Model"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 "layer_norm_epsilon": 1e-05,14 "model_type": "gpt2",15 "n_embd": 32,16 "n_head": 4,17 "n_inner": 37,18 "n_layer": 5,19 "n_positions": 512,20 "pad_token_id": 1023,21 "reorder_and_upcast_attn": false,22 "resid_pdrop": 0.1,23 "scale_attn_by_inverse_layer_idx": false,24 "scale_attn_weights": true,25 "summary_activation": null,26 "summary_first_dropout": 0.1,27 "summary_proj_to_labels": true,28 "summary_type": "cls_index",29 "summary_use_proj": true,30 "torch_dtype": "float32",31 "transformers_version": "4.28.0.dev0",32 "type_vocab_size": 16,33 "use_cache": true,34 "vocab_size": 102435}36 