c-bone/CrystaLLM-pi_base
1811
1{2 "activation_function": "gelu_new",3 "architectures": [4 "GPT2LMHeadModel"5 ],6 "attn_pdrop": 0.1,7 "bos_token_id": 372,8 "embd_pdrop": 0.1,9 "eos_token_id": 373,10 "initializer_range": 0.02,11 "layer_norm_epsilon": 1e-05,12 "model_type": "gpt2",13 "n_embd": 512,14 "n_head": 8,15 "n_inner": null,16 "n_layer": 8,17 "n_positions": 1024,18 "pad_token_id": 371,19 "reorder_and_upcast_attn": false,20 "resid_pdrop": 0.1,21 "scale_attn_by_inverse_layer_idx": false,22 "scale_attn_weights": true,23 "summary_activation": null,24 "summary_first_dropout": 0.1,25 "summary_proj_to_labels": true,26 "summary_type": "cls_index",27 "summary_use_proj": true,28 "torch_dtype": "float32",29 "transformers_version": "4.48.0",30 "use_cache": true,31 "vocab_size": 37732}33 