Clover-Hill/MemoryDecoder-gpt2-small

1{2  "_attn_implementation_autoset": true,3  "_name_or_path": "/fs-computility/plm/shared/jqcao/projects/neuralKNN/checkpoint/gpt2-small/finetune_E30_5e-4/best-checkpoint",4  "activation_function": "gelu_new",5  "architectures": [6    "GPT2LMHeadModel"7  ],8  "attn_pdrop": 0.1,9  "bos_token_id": 50256,10  "embd_pdrop": 0.1,11  "eos_token_id": 50256,12  "initializer_range": 0.02,13  "layer_norm_epsilon": 1e-05,14  "model_type": "gpt2",15  "n_ctx": 1024,16  "n_embd": 768,17  "n_head": 12,18  "n_inner": null,19  "n_layer": 12,20  "n_positions": 1024,21  "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": "4.49.0",38  "use_cache": true,39  "vocab_size": 5025740}41