Feature Extraction
Transformers
Safetensors
videojev
video
video-question-answering
temporal-grounding
custom_code
decision-model
Instructions to use ZhuYuhan/VideoJev-2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ZhuYuhan/VideoJev-2B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="ZhuYuhan/VideoJev-2B", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ZhuYuhan/VideoJev-2B", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download conversion.json from ZhuYuhan/VideoJev-2B: direct link, hf CLI and curl.
- Browser
- Download file 407 Bytes
-
https://huggingface.co/ZhuYuhan/VideoJev-2B/resolve/main/conversion.json
- Command line
-
hf download hf://ZhuYuhan/VideoJev-2B/conversion.json
-
curl -L -o conversion.json https://huggingface.co/ZhuYuhan/VideoJev-2B/resolve/main/conversion.json
407 Bytes
| { | |
| "precision_policy": "qwen_backbone_per_tensor_dtype_head_float32", | |
| "source_revision": "9d1e46dec73b9103cab3a180067d8c7493df4b1e", | |
| "base_revision": "15852e8c16360a2fea060d615a32b45270f8a8fc", | |
| "tensors": 618, | |
| "tensor_bytes": 4359379652, | |
| "shards": 3, | |
| "converted_tensors": 577, | |
| "expected_cast_values_verified": true, | |
| "parameters_by_dtype": { | |
| "BF16": 2175488288, | |
| "F32": 2100769 | |
| } | |
| } | |