BreadAi/MuseCan
0634
1{2 "activation_function": "gelu_new",3 "architectures": [4 "GPT2LMHeadModel"5 ],6 "attn_pdrop": 0,7 "bos_token_id": 0,8 "embd_pdrop": 0,9 "eos_token_id": 0,10 "initializer_range": 0.02,11 "layer_norm_epsilon": 1e-05,12 "line_by_line": false,13 "model_type": "gpt2",14 "n_ctx": 4096,15 "n_embd": 960,16 "n_head": 15,17 "n_inner": 9,18 "n_layer": 5,19 "n_positions": 4096,20 "reorder_and_upcast_attn": false,21 "resid_pdrop": 0,22 "scale_attn_by_inverse_layer_idx": false,23 "scale_attn_weights": true,24 "summary_activation": null,25 "summary_first_dropout": 0,26 "summary_proj_to_labels": true,27 "summary_type": "cls_index",28 "summary_use_proj": true,29 "torch_dtype": "float32",30 "transformers_version": "4.26.1",31 "use_cache": true,32 "vocab_size": 5030433}34 