| { | |
| "architectures": [ | |
| "InternVLChatModel" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "OpenGVLab/InternVL3-38B--configuration_internvl_chat.InternVLChatConfig", | |
| "AutoModel": "OpenGVLab/InternVL3-38B--modeling_internvl_chat.InternVLChatModel", | |
| "AutoModelForCausalLM": "OpenGVLab/InternVL3-38B--modeling_internvl_chat.InternVLChatModel" | |
| }, | |
| "downsample_ratio": 0.5, | |
| "dynamic_image_size": true, | |
| "force_image_size": 448, | |
| "hidden_size": 5120, | |
| "image_fold": null, | |
| "llm_config": { | |
| "_name_or_path": "./pretrained/Qwen2.5-32B-Instruct", | |
| "architectures": [ | |
| "Qwen2ForCausalLM" | |
| ], | |
| "attention_dropout": 0.0, | |
| "bos_token_id": 151643, | |
| "eos_token_id": 151643, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 27648, | |
| "max_position_embeddings": 32768, | |
| "max_window_layers": 70, | |
| "model_type": "qwen2", | |
| "moe_config": null, | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 64, | |
| "num_key_value_heads": 8, | |
| "rms_norm_eps": 1e-06, | |
| "rope_scaling": { | |
| "factor": 2.0, | |
| "rope_type": "dynamic", | |
| "type": "dynamic" | |
| }, | |
| "rope_theta": 1000000.0, | |
| "sliding_window": null, | |
| "torch_dtype": "bfloat16", | |
| "use_bfloat16": true, | |
| "use_cache": false, | |
| "use_sliding_window": false, | |
| "vocab_size": 151674 | |
| }, | |
| "max_dynamic_patch": 12, | |
| "min_dynamic_patch": 1, | |
| "model_type": "internvl_chat", | |
| "pad2square": false, | |
| "ps_version": "v2", | |
| "quantization_config": { | |
| "config_groups": { | |
| "group_0": { | |
| "input_activations": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": true, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": null, | |
| "observer_kwargs": {}, | |
| "strategy": "token", | |
| "symmetric": true, | |
| "type": "float" | |
| }, | |
| "output_activations": null, | |
| "targets": [ | |
| "Linear" | |
| ], | |
| "weights": { | |
| "actorder": null, | |
| "block_structure": null, | |
| "dynamic": false, | |
| "group_size": null, | |
| "num_bits": 8, | |
| "observer": "minmax", | |
| "observer_kwargs": {}, | |
| "strategy": "channel", | |
| "symmetric": true, | |
| "type": "float" | |
| } | |
| } | |
| }, | |
| "format": "float-quantized", | |
| "global_compression_ratio": null, | |
| "ignore": [ | |
| "vision_model.encoder.layers.0.attn.qkv", | |
| "vision_model.encoder.layers.0.attn.proj", | |
| "vision_model.encoder.layers.0.mlp.fc1", | |
| "vision_model.encoder.layers.0.mlp.fc2", | |
| "vision_model.encoder.layers.1.attn.qkv", | |
| "vision_model.encoder.layers.1.attn.proj", | |
| "vision_model.encoder.layers.1.mlp.fc1", | |
| "vision_model.encoder.layers.1.mlp.fc2", | |
| "vision_model.encoder.layers.2.attn.qkv", | |
| "vision_model.encoder.layers.2.attn.proj", | |
| "vision_model.encoder.layers.2.mlp.fc1", | |
| "vision_model.encoder.layers.2.mlp.fc2", | |
| "vision_model.encoder.layers.3.attn.qkv", | |
| "vision_model.encoder.layers.3.attn.proj", | |
| "vision_model.encoder.layers.3.mlp.fc1", | |
| "vision_model.encoder.layers.3.mlp.fc2", | |
| "vision_model.encoder.layers.4.attn.qkv", | |
| "vision_model.encoder.layers.4.attn.proj", | |
| "vision_model.encoder.layers.4.mlp.fc1", | |
| "vision_model.encoder.layers.4.mlp.fc2", | |
| "vision_model.encoder.layers.5.attn.qkv", | |
| "vision_model.encoder.layers.5.attn.proj", | |
| "vision_model.encoder.layers.5.mlp.fc1", | |
| "vision_model.encoder.layers.5.mlp.fc2", | |
| "vision_model.encoder.layers.6.attn.qkv", | |
| "vision_model.encoder.layers.6.attn.proj", | |
| "vision_model.encoder.layers.6.mlp.fc1", | |
| "vision_model.encoder.layers.6.mlp.fc2", | |
| "vision_model.encoder.layers.7.attn.qkv", | |
| "vision_model.encoder.layers.7.attn.proj", | |
| "vision_model.encoder.layers.7.mlp.fc1", | |
| "vision_model.encoder.layers.7.mlp.fc2", | |
| "vision_model.encoder.layers.8.attn.qkv", | |
| "vision_model.encoder.layers.8.attn.proj", | |
| "vision_model.encoder.layers.8.mlp.fc1", | |
| "vision_model.encoder.layers.8.mlp.fc2", | |
| "vision_model.encoder.layers.9.attn.qkv", | |
| "vision_model.encoder.layers.9.attn.proj", | |
| "vision_model.encoder.layers.9.mlp.fc1", | |
| "vision_model.encoder.layers.9.mlp.fc2", | |
| "vision_model.encoder.layers.10.attn.qkv", | |
| "vision_model.encoder.layers.10.attn.proj", | |
| "vision_model.encoder.layers.10.mlp.fc1", | |
| "vision_model.encoder.layers.10.mlp.fc2", | |
| "vision_model.encoder.layers.11.attn.qkv", | |
| "vision_model.encoder.layers.11.attn.proj", | |
| "vision_model.encoder.layers.11.mlp.fc1", | |
| "vision_model.encoder.layers.11.mlp.fc2", | |
| "vision_model.encoder.layers.12.attn.qkv", | |
| "vision_model.encoder.layers.12.attn.proj", | |
| "vision_model.encoder.layers.12.mlp.fc1", | |
| "vision_model.encoder.layers.12.mlp.fc2", | |
| "vision_model.encoder.layers.13.attn.qkv", | |
| "vision_model.encoder.layers.13.attn.proj", | |
| "vision_model.encoder.layers.13.mlp.fc1", | |
| "vision_model.encoder.layers.13.mlp.fc2", | |
| "vision_model.encoder.layers.14.attn.qkv", | |
| "vision_model.encoder.layers.14.attn.proj", | |
| "vision_model.encoder.layers.14.mlp.fc1", | |
| "vision_model.encoder.layers.14.mlp.fc2", | |
| "vision_model.encoder.layers.15.attn.qkv", | |
| "vision_model.encoder.layers.15.attn.proj", | |
| "vision_model.encoder.layers.15.mlp.fc1", | |
| "vision_model.encoder.layers.15.mlp.fc2", | |
| "vision_model.encoder.layers.16.attn.qkv", | |
| "vision_model.encoder.layers.16.attn.proj", | |
| "vision_model.encoder.layers.16.mlp.fc1", | |
| "vision_model.encoder.layers.16.mlp.fc2", | |
| "vision_model.encoder.layers.17.attn.qkv", | |
| "vision_model.encoder.layers.17.attn.proj", | |
| "vision_model.encoder.layers.17.mlp.fc1", | |
| "vision_model.encoder.layers.17.mlp.fc2", | |
| "vision_model.encoder.layers.18.attn.qkv", | |
| "vision_model.encoder.layers.18.attn.proj", | |
| "vision_model.encoder.layers.18.mlp.fc1", | |
| "vision_model.encoder.layers.18.mlp.fc2", | |
| "vision_model.encoder.layers.19.attn.qkv", | |
| "vision_model.encoder.layers.19.attn.proj", | |
| "vision_model.encoder.layers.19.mlp.fc1", | |
| "vision_model.encoder.layers.19.mlp.fc2", | |
| "vision_model.encoder.layers.20.attn.qkv", | |
| "vision_model.encoder.layers.20.attn.proj", | |
| "vision_model.encoder.layers.20.mlp.fc1", | |
| "vision_model.encoder.layers.20.mlp.fc2", | |
| "vision_model.encoder.layers.21.attn.qkv", | |
| "vision_model.encoder.layers.21.attn.proj", | |
| "vision_model.encoder.layers.21.mlp.fc1", | |
| "vision_model.encoder.layers.21.mlp.fc2", | |
| "vision_model.encoder.layers.22.attn.qkv", | |
| "vision_model.encoder.layers.22.attn.proj", | |
| "vision_model.encoder.layers.22.mlp.fc1", | |
| "vision_model.encoder.layers.22.mlp.fc2", | |
| "vision_model.encoder.layers.23.attn.qkv", | |
| "vision_model.encoder.layers.23.attn.proj", | |
| "vision_model.encoder.layers.23.mlp.fc1", | |
| "vision_model.encoder.layers.23.mlp.fc2", | |
| "vision_model.encoder.layers.24.attn.qkv", | |
| "vision_model.encoder.layers.24.attn.proj", | |
| "vision_model.encoder.layers.24.mlp.fc1", | |
| "vision_model.encoder.layers.24.mlp.fc2", | |
| "vision_model.encoder.layers.25.attn.qkv", | |
| "vision_model.encoder.layers.25.attn.proj", | |
| "vision_model.encoder.layers.25.mlp.fc1", | |
| "vision_model.encoder.layers.25.mlp.fc2", | |
| "vision_model.encoder.layers.26.attn.qkv", | |
| "vision_model.encoder.layers.26.attn.proj", | |
| "vision_model.encoder.layers.26.mlp.fc1", | |
| "vision_model.encoder.layers.26.mlp.fc2", | |
| "vision_model.encoder.layers.27.attn.qkv", | |
| "vision_model.encoder.layers.27.attn.proj", | |
| "vision_model.encoder.layers.27.mlp.fc1", | |
| "vision_model.encoder.layers.27.mlp.fc2", | |
| "vision_model.encoder.layers.28.attn.qkv", | |
| "vision_model.encoder.layers.28.attn.proj", | |
| "vision_model.encoder.layers.28.mlp.fc1", | |
| "vision_model.encoder.layers.28.mlp.fc2", | |
| "vision_model.encoder.layers.29.attn.qkv", | |
| "vision_model.encoder.layers.29.attn.proj", | |
| "vision_model.encoder.layers.29.mlp.fc1", | |
| "vision_model.encoder.layers.29.mlp.fc2", | |
| "vision_model.encoder.layers.30.attn.qkv", | |
| "vision_model.encoder.layers.30.attn.proj", | |
| "vision_model.encoder.layers.30.mlp.fc1", | |
| "vision_model.encoder.layers.30.mlp.fc2", | |
| "vision_model.encoder.layers.31.attn.qkv", | |
| "vision_model.encoder.layers.31.attn.proj", | |
| "vision_model.encoder.layers.31.mlp.fc1", | |
| "vision_model.encoder.layers.31.mlp.fc2", | |
| "vision_model.encoder.layers.32.attn.qkv", | |
| "vision_model.encoder.layers.32.attn.proj", | |
| "vision_model.encoder.layers.32.mlp.fc1", | |
| "vision_model.encoder.layers.32.mlp.fc2", | |
| "vision_model.encoder.layers.33.attn.qkv", | |
| "vision_model.encoder.layers.33.attn.proj", | |
| "vision_model.encoder.layers.33.mlp.fc1", | |
| "vision_model.encoder.layers.33.mlp.fc2", | |
| "vision_model.encoder.layers.34.attn.qkv", | |
| "vision_model.encoder.layers.34.attn.proj", | |
| "vision_model.encoder.layers.34.mlp.fc1", | |
| "vision_model.encoder.layers.34.mlp.fc2", | |
| "vision_model.encoder.layers.35.attn.qkv", | |
| "vision_model.encoder.layers.35.attn.proj", | |
| "vision_model.encoder.layers.35.mlp.fc1", | |
| "vision_model.encoder.layers.35.mlp.fc2", | |
| "vision_model.encoder.layers.36.attn.qkv", | |
| "vision_model.encoder.layers.36.attn.proj", | |
| "vision_model.encoder.layers.36.mlp.fc1", | |
| "vision_model.encoder.layers.36.mlp.fc2", | |
| "vision_model.encoder.layers.37.attn.qkv", | |
| "vision_model.encoder.layers.37.attn.proj", | |
| "vision_model.encoder.layers.37.mlp.fc1", | |
| "vision_model.encoder.layers.37.mlp.fc2", | |
| "vision_model.encoder.layers.38.attn.qkv", | |
| "vision_model.encoder.layers.38.attn.proj", | |
| "vision_model.encoder.layers.38.mlp.fc1", | |
| "vision_model.encoder.layers.38.mlp.fc2", | |
| "vision_model.encoder.layers.39.attn.qkv", | |
| "vision_model.encoder.layers.39.attn.proj", | |
| "vision_model.encoder.layers.39.mlp.fc1", | |
| "vision_model.encoder.layers.39.mlp.fc2", | |
| "vision_model.encoder.layers.40.attn.qkv", | |
| "vision_model.encoder.layers.40.attn.proj", | |
| "vision_model.encoder.layers.40.mlp.fc1", | |
| "vision_model.encoder.layers.40.mlp.fc2", | |
| "vision_model.encoder.layers.41.attn.qkv", | |
| "vision_model.encoder.layers.41.attn.proj", | |
| "vision_model.encoder.layers.41.mlp.fc1", | |
| "vision_model.encoder.layers.41.mlp.fc2", | |
| "vision_model.encoder.layers.42.attn.qkv", | |
| "vision_model.encoder.layers.42.attn.proj", | |
| "vision_model.encoder.layers.42.mlp.fc1", | |
| "vision_model.encoder.layers.42.mlp.fc2", | |
| "vision_model.encoder.layers.43.attn.qkv", | |
| "vision_model.encoder.layers.43.attn.proj", | |
| "vision_model.encoder.layers.43.mlp.fc1", | |
| "vision_model.encoder.layers.43.mlp.fc2", | |
| "vision_model.encoder.layers.44.attn.qkv", | |
| "vision_model.encoder.layers.44.attn.proj", | |
| "vision_model.encoder.layers.44.mlp.fc1", | |
| "vision_model.encoder.layers.44.mlp.fc2", | |
| "language_model.lm_head" | |
| ], | |
| "kv_cache_scheme": null, | |
| "quant_method": "compressed-tensors", | |
| "quantization_status": "compressed" | |
| }, | |
| "select_layer": -1, | |
| "system_message": null, | |
| "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-V1-5", | |
| "architectures": [ | |
| "InternVisionModel" | |
| ], | |
| "attention_dropout": 0.0, | |
| "auto_map": { | |
| "AutoConfig": "configuration_intern_vit.InternVisionConfig", | |
| "AutoModel": "modeling_intern_vit.InternVisionModel" | |
| }, | |
| "capacity_factor": 1.2, | |
| "drop_path_rate": 0.4, | |
| "dropout": 0.0, | |
| "eval_capacity_factor": 1.4, | |
| "hidden_act": "gelu", | |
| "hidden_size": 3200, | |
| "image_size": 448, | |
| "initializer_factor": 0.1, | |
| "initializer_range": 1e-10, | |
| "intermediate_size": 12800, | |
| "laux_allreduce": "all_nodes", | |
| "layer_norm_eps": 1e-06, | |
| "model_type": "intern_vit_6b", | |
| "moe_coeff_ratio": 0.5, | |
| "moe_intermediate_size": 768, | |
| "moe_output_scale": 4.0, | |
| "noisy_gate_policy": "RSample_before", | |
| "norm_type": "rms_norm", | |
| "num_attention_heads": 25, | |
| "num_channels": 3, | |
| "num_experts": 8, | |
| "num_hidden_layers": 45, | |
| "num_routed_experts": 4, | |
| "num_shared_experts": 4, | |
| "patch_size": 14, | |
| "qk_normalization": true, | |
| "qkv_bias": false, | |
| "shared_expert_intermediate_size": 3072, | |
| "torch_dtype": "bfloat16", | |
| "use_bfloat16": true, | |
| "use_flash_attn": false, | |
| "use_moe": false, | |
| "use_residual": true, | |
| "use_rts": false, | |
| "use_weighted_residual": false | |
| } | |
| } |