MLX
Safetensors
English
Chinese
qwen2
linux-kernel
qwen2.5
lora
fine-tuning
knowledge-distillation
4-bit precision
Instructions to use gaowanlong/kernel-lora-v0.6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use gaowanlong/kernel-lora-v0.6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir kernel-lora-v0.6 gaowanlong/kernel-lora-v0.6
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
File size: 133 Bytes
89a0f35 | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
size 11421892
|