| { | |
| "_name_or_path": "/wjn/pre-trained-lm/gpt2-large", | |
| "activation_function": "gelu_new", | |
| "adapter_choice": "LiST", | |
| "adapter_dim": 128, | |
| "architectures": [ | |
| "GPT2ForCausalLM" | |
| ], | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 50256, | |
| "embd_pdrop": 0.1, | |
| "eos_token_id": 50256, | |
| "finetuning_task": "causal_instruction", | |
| "hidden_dropout_prob": 0.1, | |
| "initializer_range": 0.02, | |
| "layer_norm_epsilon": 1e-05, | |
| "model_type": "gpt2", | |
| "n_ctx": 1024, | |
| "n_embd": 1280, | |
| "n_head": 20, | |
| "n_inner": null, | |
| "n_layer": 36, | |
| "n_positions": 1024, | |
| "pre_seq_len": 4, | |
| "prefix_hidden_size": 512, | |
| "prefix_projection": false, | |
| "reorder_and_upcast_attn": false, | |
| "resid_pdrop": 0.1, | |
| "scale_attn_by_inverse_layer_idx": false, | |
| "scale_attn_weights": true, | |
| "summary_activation": null, | |
| "summary_first_dropout": 0.1, | |
| "summary_proj_to_labels": true, | |
| "summary_type": "cls_index", | |
| "summary_use_proj": true, | |
| "task_specific_params": { | |
| "text-generation": { | |
| "do_sample": true, | |
| "max_length": 50 | |
| } | |
| }, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.21.2", | |
| "use_cache": true, | |
| "use_freezing": false, | |
| "use_prompt_for_cls": false, | |
| "vocab_size": 50257 | |
| } | |