{ "_name_or_path": "deepseek-ai/deepseek-coder-7b-instruct-v1.5", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "bos_token_id": 100000, "eos_token_id": 100001, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 4096, "model_type": "llama", "num_attention_heads": 32, "num_hidden_layers": 30, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.35.2", "use_cache": true, "vocab_size": 102400 }