{ "_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct", "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 32013, "eos_token_id": 32021, "freeze_mm_mlp_adapter": false, "hidden_act": "silu", "hidden_size": 4096, "image_aspect_ratio": "pad", "initializer_range": 0.02, "intermediate_size": 11008, "max_position_embeddings": 16384, "mm_hidden_size": 1152, "mm_patch_merge_type": "flat", "mm_projector_lr": 2e-05, "mm_projector_type": "mlp2x_gelu", "mm_use_im_patch_token": false, "mm_use_im_start_end": false, "mm_vision_select_feature": "patch", "mm_vision_select_layer": -2, "mm_vision_tower": "google/siglip-so400m-patch14-384", "model_type": "llava_llama", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 32, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": { "factor": 4.0, "type": "linear" }, "rope_theta": 100000, "s2": false, "s2_scales": "336,672,1008", "tie_word_embeddings": false, "tokenizer_model_max_length": 4096, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.37.2", "tune_mm_mlp_adapter": false, "use_cache": true, "use_mm_proj": true, "vocab_size": 32256 }