{ "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "architectures": [ "DeepSeekLlavaModel" ], "ignore_index": -100, "image_seq_length": 576, "image_token_index": 151665, "language_model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "model_type": "deepseek_llava", "multimodal_projector_bias": true, "projector_hidden_act": "gelu", "text_config": { "model_type": "llama" }, "text_hidden_size": 1536, "torch_dtype": "float32", "transformers_version": "4.49.0.dev0", "vision_config": { "hidden_size": 1024, "image_size": 336, "intermediate_size": 4096, "model_type": "clip_vision_model", "num_attention_heads": 16, "num_hidden_layers": 24, "patch_size": 14, "projection_dim": 768, "vocab_size": 32000 }, "vision_feature_layer": -2, "vision_feature_select_strategy": "default", "vision_hidden_size": 1024, "vision_model_name": "openai/clip-vit-large-patch14" }