{ "architectures": [ "KimiVLForConditionalGeneration" ], "auto_map": { "AutoConfig": "moonshotai/Kimi-VL-A3B-Thinking-2506--configuration_kimi_vl.KimiVLConfig", "AutoModel": "moonshotai/Kimi-VL-A3B-Thinking-2506--modeling_kimi_vl.KimiVLForConditionalGeneration", "AutoModelForCausalLM": "moonshotai/Kimi-VL-A3B-Thinking-2506--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": "float16", "bnb_4bit_quant_storage": "uint8", "bnb_4bit_quant_type": "nf4", "bnb_4bit_use_double_quant": true, "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": { "attention_bias": false, "attention_dropout": 0.0, "aux_loss_alpha": 0.001, "bos_token_id": 163584, "eos_token_id": 163585, "ep_size": 1, "first_k_dense_replace": 1, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 11264, "kv_lora_rank": 512, "max_position_embeddings": 131072, "model_type": "deepseek_v3", "moe_intermediate_size": 1408, "moe_layer_freq": 1, "n_group": 1, "n_routed_experts": 64, "n_shared_experts": 2, "norm_topk_prob": true, "num_attention_heads": 16, "num_experts_per_tok": 6, "num_hidden_layers": 27, "num_key_value_heads": 16, "num_nextn_predict_layers": 1, "pad_token_id": 163839, "pretraining_tp": 1, "q_lora_rank": null, "qk_nope_head_dim": 128, "qk_rope_head_dim": 64, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 800000.0, "routed_scaling_factor": 2.446, "scoring_func": "sigmoid", "seq_aux": true, "topk_group": 1, "topk_method": "noaux_tc", "torch_dtype": "bfloat16", "use_cache": true, "v_head_dim": 128, "vocab_size": 163840 }, "tie_word_embeddings": false, "torch_dtype": "float16", "transformers_version": "4.52.4", "vision_config": { "hidden_size": 1152, "init_pos_emb_height": 64, "init_pos_emb_width": 64, "intermediate_size": 4304, "merge_kernel_size": [ 2, 2 ], "model_type": "moonvit", "num_attention_heads": 16, "num_hidden_layers": 27, "patch_size": 14, "torch_dtype": "bfloat16" }, "vocab_size": 163840 }