Instructions to use OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-13B-448px with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-13B-448px with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-13B-448px")# Load model directly from transformers import AutoProcessor, AutoModelForCausalLM processor = AutoProcessor.from_pretrained("OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-13B-448px") model = AutoModelForCausalLM.from_pretrained("OpenGVLab/InternVL-Chat-ViT-6B-Vicuna-13B-448px") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "./pretrained/vicuna-13b-v1.5", | |
| "architectures": [ | |
| "LlavaLlamaForCausalLM" | |
| ], | |
| "bos_token_id": 1, | |
| "eos_token_id": 2, | |
| "freeze_mm_mlp_adapter": false, | |
| "hidden_act": "silu", | |
| "hidden_size": 5120, | |
| "image_aspect_ratio": "pad", | |
| "image_grid_pinpoints": null, | |
| "initializer_range": 0.02, | |
| "intermediate_size": 13824, | |
| "max_length": 4096, | |
| "max_position_embeddings": 4096, | |
| "mm_hidden_size": 3200, | |
| "mm_projector_type": "mlp2x_gelu", | |
| "mm_use_im_patch_token": false, | |
| "mm_use_im_start_end": false, | |
| "mm_vision_select_feature": "patch", | |
| "mm_vision_select_layer": -4, | |
| "mm_vision_tower": "OpenGVLab/InternViT-6B-448px-V1-0", | |
| "model_type": "llava", | |
| "num_attention_heads": 40, | |
| "num_hidden_layers": 40, | |
| "num_key_value_heads": 40, | |
| "pad_token_id": 0, | |
| "pretraining_tp": 1, | |
| "rms_norm_eps": 1e-05, | |
| "rope_scaling": null, | |
| "tie_word_embeddings": false, | |
| "torch_dtype": "bfloat16", | |
| "transformers_version": "4.32.0", | |
| "tune_mm_mlp_adapter": false, | |
| "tune_vit_pos_embedding": false, | |
| "use_cache": true, | |
| "use_mm_proj": true, | |
| "vocab_size": 32000 | |
| } | |