rnaveensrinivas/Instruct_GPT_small

1{2  "_name_or_path": "Sharathhebbar24/SSH_300M",3  "activation_function": "gelu_new",4  "architectures": [5    "GPT2LMHeadModel"6  ],7  "attn_pdrop": 0.1,8  "bos_token_id": 50256,9  "embd_pdrop": 0.1,10  "eos_token_id": 50256,11  "initializer_range": 0.02,12  "layer_norm_epsilon": 1e-05,13  "model_type": "gpt2",14  "n_ctx": 1024,15  "n_embd": 1024,16  "n_head": 16,17  "n_inner": null,18  "n_layer": 24,19  "n_positions": 1024,20  "n_special": 0,21  "predict_special_tokens": true,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": "4.41.2",39  "use_cache": true,40  "vocab_size": 5025741}42