parallelm/gpt2_small_EN_superbpe_8192_parallel10_42

1{2  "_name_or_path": "models/gpt2_small_EN_superbpe_8192_parallel10_42",3  "activation_function": "gelu_new",4  "architectures": [5    "GPT2LMHeadModel"6  ],7  "attn_pdrop": 0.1,8  "bos_token_id": 2,9  "embd_pdrop": 0.1,10  "eos_token_id": 2,11  "initializer_range": 0.02,12  "layer_norm_epsilon": 1e-05,13  "model_type": "gpt2",14  "n_ctx": 1024,15  "n_embd": 768,16  "n_head": 12,17  "n_inner": null,18  "n_layer": 12,19  "n_positions": 128,20  "pad_token_id": 1,21  "reorder_and_upcast_attn": false,22  "resid_pdrop": 0.1,23  "scale_attn_by_inverse_layer_idx": false,24  "scale_attn_weights": true,25  "summary_activation": null,26  "summary_first_dropout": 0.1,27  "summary_proj_to_labels": true,28  "summary_type": "cls_index",29  "summary_use_proj": true,30  "task_specific_params": {31    "text-generation": {32      "do_sample": true,33      "max_length": 5034    }35  },36  "torch_dtype": "float32",37  "transformers_version": "4.41.2",38  "use_cache": true,39  "vocab_size": 819240}41