harikrushna2272/github_code_codeparrot
029
1{2 "activation_function": "gelu_new",3 "architectures": [4 "GPT2LMHeadModel"5 ],6 "attn_pdrop": 0.1,7 "bos_token_id": 50256,8 "do_sample": null,9 "embd_pdrop": 0.1,10 "eos_token_id": 50256,11 "gradient_checkpointing": false,12 "initializer_range": 0.02,13 "layer_norm_epsilon": 1e-05,14 "max_length": null,15 "model_type": "gpt2",16 "n_ctx": 128,17 "n_embd": 768,18 "n_head": 12,19 "n_inner": null,20 "n_layer": 12,21 "n_positions": 1024,22 "reorder_and_upcast_attn": false,23 "resid_pdrop": 0.1,24 "scale_attn_by_inverse_layer_idx": false,25 "scale_attn_weights": true,26 "summary_activation": null,27 "summary_first_dropout": 0.1,28 "summary_proj_to_labels": true,29 "summary_type": "cls_index",30 "summary_use_proj": true,31 "task_specific_params": {32 "text-generation": {33 "do_sample": true,34 "max_length": 5035 }36 },37 "torch_dtype": "float32",38 "transformers_version": "4.53.1",39 "use_cache": true,40 "vocab_size": 5000041}42 