{ "_name_or_path": "/workspace/opus-v1-34b", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 7168, "initializer_range": 0.02, "intermediate_size": 20480, "max_position_embeddings": 200000, "model_type": "llama", "num_attention_heads": 56, "num_hidden_layers": 60, "num_key_value_heads": 8, "pad_token_id": 0, "pretraining_tp": 1, "quantization_config": { "bits": 4, "group_size": 128, "modules_to_not_convert": null, "quant_method": "awq", "version": "gemm", "zero_point": true }, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 5000000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.37.2", "use_cache": false, "vocab_size": 64000 }