chirag2706/gpt2_code_generation_model
034
1{2 "activation_function": "gelu_new",3 "architectures": [4 "GPT2LMHeadModel"5 ],6 "attn_pdrop": 0.1,7 "bos_token_id": 50256,8 "embd_pdrop": 0.1,9 "eos_token_id": 50256,10 "initializer_range": 0.02,11 "layer_norm_epsilon": 1e-05,12 "model_type": "gpt2",13 "n_ctx": 1024,14 "n_embd": 1024,15 "n_head": 16,16 "n_layer": 24,17 "n_positions": 1024,18 "n_special": 0,19 "predict_special_tokens": true,20 "resid_pdrop": 0.1,21 "summary_activation": null,22 "summary_first_dropout": 0.1,23 "summary_proj_to_labels": true,24 "summary_type": "cls_index",25 "summary_use_proj": true,26 "task_specific_params": {27 "text-generation": {28 "do_sample": true,29 "max_length": 5030 }31 },32 "vocab_size": 5026033}34 