{ "architectures": [ "InternVLChatModel" ], "auto_map": { "AutoConfig": "configuration_h2ovl_chat.H2OVLChatConfig", "AutoModel": "modelling_h2ovl_chat.H2OVLChatModel", "AutoModelForCausalLM": "modelling_h2ovl_chat.H2OVLChatModel" }, "downsample_ratio": 0.5, "dynamic_image_size": true, "force_image_size": 448, "llm_config": { "_name_or_path": "h2oai/h2o-danube3-500m-chat", "add_cross_attention": false, "architectures": [ "LlamaForCausalLM" ], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "encoder_no_repeat_ngram_size": 0, "eos_token_id": 2, "exponential_decay_length_penalty": null, "finetuning_task": null, "hidden_act": "silu", "hidden_size": 1536, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "length_penalty": 1.0, "max_position_embeddings": 8192, "mlp_bias": false, "model_type": "llama", "num_attention_heads": 16, "num_hidden_layers": 16, "num_key_value_heads": 8, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": 0, "prefix": null, "pretraining_tp": 1, "problem_type": null, "pruned_heads": {}, "remove_invalid_values": false, "return_dict": true, "return_dict_in_generate": false, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 100000, "sep_token_id": null, "sliding_window": null, "suppress_tokens": null, "task_specific_params": null, "tie_encoder_decoder": false, "tie_word_embeddings": false, "tokenizer_class": null, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.42.0.dev0", "use_bfloat16": false, "use_cache": true, "vocab_size": 32010 }, "max_dynamic_patch": 6, "min_dynamic_patch": 1, "model_type": "internvl_chat", "pad2square": false, "ps_version": "v2", "select_layer": -1, "template": "h2ogpt2", "torch_dtype": "bfloat16", "transformers_version": null, "use_backbone_lora": 0, "use_llm_lora": 0, "use_thumbnail": true, "use_msac": false, "vision_config": { "_name_or_path": "OpenGVLab/InternViT-300M-448px", "add_cross_attention": false, "architectures": [ "InternVisionModel" ], "attention_dropout": 0.0, "auto_map": { "AutoConfig": "OpenGVLab/InternViT-300M-448px--configuration_intern_vit.InternVisionConfig", "AutoModel": "OpenGVLab/InternViT-300M-448px--modeling_intern_vit.InternVisionModel" }, "bos_token_id": null, "chunk_size_feed_forward": 0, "cross_attention_hidden_size": null, "decoder_start_token_id": null, "drop_path_rate": 0.0, "dropout": 0.0, "eos_token_id": null, "exponential_decay_length_penalty": null, "finetuning_task": null, "hidden_act": "gelu", "hidden_size": 1024, "image_size": 448, "initializer_factor": 1.0, "initializer_range": 0.02, "intermediate_size": 4096, "is_decoder": false, "is_encoder_decoder": false, "layer_norm_eps": 1e-06, "length_penalty": 1.0, "max_length": 20, "min_length": 0, "model_type": "intern_vit_6b", "no_repeat_ngram_size": 0, "norm_type": "layer_norm", "num_attention_heads": 16, "num_beam_groups": 1, "num_beams": 1, "num_channels": 3, "num_hidden_layers": 24, "num_return_sequences": 1, "output_attentions": false, "output_hidden_states": false, "output_scores": false, "pad_token_id": null, "patch_size": 14, "prefix": null, "problem_type": null, "pruned_heads": {}, "qk_normalization": false, "qkv_bias": true, "remove_invalid_values": false, "repetition_penalty": 1.0, "return_dict": true, "return_dict_in_generate": false, "sep_token_id": null, "task_specific_params": null, "tie_encoder_decoder": false, "tie_word_embeddings": true, "tokenizer_class": null, "torch_dtype": "bfloat16", "torchscript": false, "transformers_version": "4.42.0.dev0", "use_bfloat16": false, "use_flash_attn": true } }