{ "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", "AutoModel": "modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "eos_token_id": 151645, "force_image_size": 448, "llm_config": { "_name_or_path": "/root/codespace/checkpoints/Qwen3-235B-A22B", "architectures": [ "Qwen3MoeForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 151643, "decoder_sparse_step": 1, "eos_token_id": 151645, "head_dim": 128, "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 12288, "max_position_embeddings": 40960, "max_window_layers": 94, "mlp_only_layers": [], "model_type": "qwen3_moe", "moe_intermediate_size": 1536, "norm_topk_prob": true, "num_attention_heads": 64, "num_experts": 128, "num_experts_per_tok": 8, "num_hidden_layers": 94, "num_key_value_heads": 4, "output_router_logits": false, "rms_norm_eps": 1e-06, "rope_scaling": null, "rope_theta": 1000000.0, "router_aux_loss_coef": 0.001, "sliding_window": null, "torch_dtype": "bfloat16", "use_cache": true, "use_sliding_window": false, "vocab_size": 151936 }, "max_dynamic_patch": 12, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "pad_token_id": 151643, "ps_version": "v2", "select_layer": -1, "template": "internvl2_5", "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_name_or_path": "OpenGVLab/InternViT-6B-448px-V2_5", "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "configuration_intern_vit.InternVisionConfig", "AutoModel": "modeling_intern_vit.InternVisionModel" }, "drop_path_rate": 0.1, "dropout": 0.0, "hidden_act": "gelu", "hidden_size": 3200, "image_size": 448, "initializer_factor": 0.1, "initializer_range": 1e-10, "intermediate_size": 12800, "layer_norm_eps": 1e-06, "model_type": "intern_vit_6b", "norm_type": "rms_norm", "num_attention_heads": 25, "num_channels": 3, "num_hidden_layers": 45, "patch_size": 14, "qk_normalization": true, "qkv_bias": false, "torch_dtype": "bfloat16", "use_bfloat16": true, "use_flash_attn": true } }