Instructions to use d-shlenskii/VideoLLava-demo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use d-shlenskii/VideoLLava-demo with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("d-shlenskii/VideoLLava-demo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download adapter_config.json from d-shlenskii/VideoLLava-demo: direct link, hf CLI and curl.
- Browser
- Download file 895 Bytes
-
https://huggingface.co/d-shlenskii/VideoLLava-demo/resolve/main/adapter_config.json
- Command line
-
hf download hf://d-shlenskii/VideoLLava-demo/adapter_config.json
-
curl -L -o adapter_config.json https://huggingface.co/d-shlenskii/VideoLLava-demo/resolve/main/adapter_config.json
895 Bytes
| { | |
| "alpha_pattern": {}, | |
| "auto_mapping": { | |
| "base_model_class": "InternVLChatModel", | |
| "parent_library": "transformers_modules.OpenGVLab.InternVL2-1B.a84c71e158b16180df4fd1c5fe963fdf54b2cd43.modeling_internvl_chat" | |
| }, | |
| "base_model_name_or_path": "OpenGVLab/InternVL2-1B", | |
| "bias": "none", | |
| "fan_in_fan_out": false, | |
| "inference_mode": true, | |
| "init_lora_weights": true, | |
| "layer_replication": null, | |
| "layers_pattern": null, | |
| "layers_to_transform": null, | |
| "loftq_config": {}, | |
| "lora_alpha": 96, | |
| "lora_dropout": 0.0, | |
| "megatron_config": null, | |
| "megatron_core": "megatron.core", | |
| "modules_to_save": null, | |
| "peft_type": "LORA", | |
| "r": 24, | |
| "rank_pattern": {}, | |
| "revision": null, | |
| "target_modules": [ | |
| "gate_proj", | |
| "q_proj", | |
| "up_proj", | |
| "v_proj", | |
| "k_proj", | |
| "o_proj", | |
| "down_proj" | |
| ], | |
| "task_type": null, | |
| "use_dora": false, | |
| "use_rslora": false | |
| } |