| { | |
| "_name_or_path": "test", | |
| "activation_dropout": 0.0, | |
| "activation_function": "gelu_new", | |
| "architectures": [ | |
| "OPTForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "attn_pdrop": 0.1, | |
| "bos_token_id": 2, | |
| "classifier_dropout": 0.0, | |
| "d_model": 1024, | |
| "decoder_attention_heads": 16, | |
| "decoder_ffn_dim": 4096, | |
| "decoder_layerdrop": 0.0, | |
| "decoder_layers": 24, | |
| "decoder_start_token_id": 2, | |
| "do_sample": true, | |
| "dropout": 0.1, | |
| "embd_pdrop": 0.1, | |
| "embed_dim": 512, | |
| "eos_token_id": 50256, | |
| "forced_eos_token_id": 2, | |
| "id2label": { | |
| "0": "LABEL_0", | |
| "1": "LABEL_1", | |
| "2": "LABEL_2" | |
| }, | |
| "init_std": 0.02, | |
| "initializer_range": 0.02, | |
| "is_decoder": true, | |
| "is_encoder_decoder": false, | |
| "label2id": { | |
| "LABEL_0": 0, | |
| "LABEL_1": 1, | |
| "LABEL_2": 2 | |
| }, | |
| "layer_norm_epsilon": 1e-05, | |
| "max_length": 50, | |
| "max_position_embeddings": 2048, | |
| "model_type": "opt", | |
| "n_ctx": 1024, | |
| "n_embd": 768, | |
| "n_head": 12, | |
| "n_layer": 12, | |
| "n_positions": 1024, | |
| "pad_token_id": 1, | |
| "resid_pdrop": 0.1, | |
| "scale_embedding": false, | |
| "share_input_output_embed": 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": "4.19.0.dev0", | |
| "use_cache": false, | |
| "vocab_size": 50272 | |
| } | |