{ "_name_or_path": "models/Kimi-VL-A3B-Thinking/Kimi-VL-A3B-Thinking", "architectures": [ "KimiVLForConditionalGeneration" ], "auto_map": { "AutoConfig": "configuration_kimi_vl.KimiVLConfig", "AutoModel": "modeling_kimi_vl.KimiVLForConditionalGeneration", "AutoModelForCausalLM": "modeling_kimi_vl.KimiVLForConditionalGeneration" }, "ignore_index": -100, "media_placeholder_token_id": 163605, "model_type": "kimi_vl", "pad_token_id": 0, "quantization_config": { "_load_in_4bit": true, "_load_in_8bit": false, "bnb_4bit_compute_dtype": "float32", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "fp4", "bnb_4bit_use_double_quant": false, "llm_int8_enable_fp32_cpu_offload": false, "llm_int8_has_fp16_weight": false, "llm_int8_skip_modules": null, "llm_int8_threshold": 6.0, "load_in_4bit": true, "load_in_8bit": false, "quant_method": "bitsandbytes" }, "text_config": { "_attn_implementation_autoset": true, "bos_token_id": 163584, "eos_token_id": 163585, "first_k_dense_replace": 1, "hidden_size": 2048, "intermediate_size": 11264, "max_position_embeddings": 131072, "model_type": "deepseek_v3", "moe_intermediate_size": 1408, "n_group": 1, "n_routed_experts": 64, "n_shared_experts": 2, "num_attention_heads": 16, "num_experts_per_tok": 6, "num_hidden_layers": 27, "num_key_value_heads": 16, "pad_token_id": 163839, "q_lora_rank": null, "rms_norm_eps": 1e-05, "rope_theta": 800000.0, "routed_scaling_factor": 2.446, "topk_group": 1, "torch_dtype": "bfloat16", "vocab_size": 163840 }, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.47.1", "vision_config": { "_attn_implementation_autoset": true, "merge_kernel_size": [ 2, 2 ], "model_type": "moonvit", "torch_dtype": "bfloat16" }, "vocab_size": 163840 }