pops-team/bittensor

1{2  "_name_or_path": "/root/pretraining/local-models/training/2024-01-07_10-32-40",3  "activation_function": "gelu_new",4  "architectures": [5    "GPT2LMHeadModel"6  ],7  "attn_pdrop": 0.0,8  "bos_token_id": 50256,9  "embd_pdrop": 0.0,10  "eos_token_id": 50256,11  "initializer_range": 0.02,12  "layer_norm_epsilon": 1e-05,13  "model_type": "gpt2",14  "n_embd": 768,15  "n_head": 12,16  "n_inner": null,17  "n_layer": 11,18  "n_positions": 1024,19  "reorder_and_upcast_attn": false,20  "resid_pdrop": 0.0,21  "scale_attn_by_inverse_layer_idx": false,22  "scale_attn_weights": true,23  "summary_activation": null,24  "summary_first_dropout": 0.0,25  "summary_proj_to_labels": true,26  "summary_type": "cls_index",27  "summary_use_proj": true,28  "torch_dtype": "float32",29  "transformers_version": "4.34.1",30  "use_cache": true,31  "vocab_size": 5025732}33