{ "_name_or_path": "/ssd003/projects/aieng/public/llm-collaboration-research//opt-350/opt-350m_sst5_mapped_grouped_1", "_remove_final_layer_norm": false, "activation_dropout": 0.0, "activation_function": "relu", "architectures": [ "OPTForSequenceClassification" ], "attention_dropout": 0.0, "bos_token_id": 2, "do_layer_norm_before": false, "dropout": 0.1, "enable_bias": true, "eos_token_id": 2, "ffn_dim": 4096, "hidden_size": 1024, "id2label": { "0": "LABEL_0", "1": "LABEL_1", "2": "LABEL_2" }, "init_std": 0.02, "label2id": { "LABEL_0": 0, "LABEL_1": 1, "LABEL_2": 2 }, "layer_norm_elementwise_affine": true, "layerdrop": 0.0, "max_position_embeddings": 2048, "model_type": "opt", "num_attention_heads": 16, "num_hidden_layers": 24, "pad_token_id": 1, "prefix": "", "torch_dtype": "float32", "transformers_version": "4.37.2", "use_cache": true, "vocab_size": 50272, "word_embed_proj_dim": 512 }