{ "_name_or_path": "deepseek-coder-1.3b-instruct", "architectures": [ "LlavaDeepseekForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 32013, "eos_token_id": 32021, "freeze_mm_mlp_adapter": false, "head_dim": 128, "hidden_act": "silu", "hidden_size": 2048, "image_aspect_ratio": "square", "initializer_range": 0.02, "intermediate_size": 5504, "max_position_embeddings": 16384, "mlp_bias": false, "mm_hidden_size": 1152, "mm_patch_merge_type": "flat", "mm_projector_lr": null, "mm_projector_type": "mlp_charluma", "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": "/your_local_path/siglip-so400m-patch14-384", "model_type": "llava_deepseekcoder", "num_attention_heads": 16, "num_hidden_layers": 24, "num_key_value_heads": 16, "pretraining_tp": 1, "rms_norm_eps": 1e-06, "rope_scaling": { "factor": 4.0, "rope_type": "linear", "type": "linear" }, "rope_theta": 100000, "tie_word_embeddings": false, "tokenizer_model_max_length": 2048, "tokenizer_padding_side": "right", "torch_dtype": "bfloat16", "transformers_version": "4.49.0", "tune_mm_mlp_adapter": false, "use_cache": true, "use_mm_proj": true, "vocab_size": 32256 }