{ "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "configuration_internvl_chat.InternVLChatConfig", "AutoModel": "modeling_internvl_chat.InternVLChatModel", "AutoModelForCausalLM": "OpenGVLab/InternVL2_5-8B--modeling_internvl_chat.InternVLChatModel" }, "downsample_ratio": 0.5, "dtype": "bfloat16", "dynamic_image_size": true, "force_image_size": 448, "hidden_size": 4096, "llm_config": { "_attn_implementation_autoset": true, "_name_or_path": "internlm/internlm2_5-7b-chat", "architectures": [ "InternLM2ForCausalLM" ], "attn_implementation": "eager", "auto_map": { "AutoConfig": "configuration_internlm2.InternLM2Config", "AutoModel": "modeling_internlm2.InternLM2ForCausalLM", "AutoModelForCausalLM": "modeling_internlm2.InternLM2ForCausalLM", "AutoModelForSequenceClassification": "modeling_internlm2.InternLM2ForSequenceClassification" }, "bias": false, "dtype": "bfloat16", "hidden_act": "silu", "hidden_size": 4096, "initializer_range": 0.02, "intermediate_size": 14336, "max_position_embeddings": 32768, "model_type": "internlm2", "num_attention_heads": 32, "num_hidden_layers": 32, "num_key_value_heads": 8, "pad_token_id": 2, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": { "factor": 2.0, "type": "dynamic" }, "rope_theta": 1000000, "use_bfloat16": true, "use_cache": false, "vocab_size": 92553 }, "max_dynamic_patch": 6, "min_dynamic_patch": 1, "model_type": "internvl_chat", "output_attentions": false, "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "internvl2_5", "tie_word_embeddings": false, "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "vision_config": { "_attn_implementation_autoset": true, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "drop_path_rate": 0.1, "dropout": 0.0, "dtype": "bfloat16", "hidden_act": "gelu", "hidden_size": 1024, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "layer_norm_eps": 1e-06, "model_type": "intern_vit_6b", "norm_type": "layer_norm", "num_attention_heads": 16, "num_channels": 3, "num_hidden_layers": 24, "patch_size": 14, "qk_normalization": false, "qkv_bias": true, "use_bfloat16": true, "use_flash_attn": false } }