Instructions to use kunal89/llama3.2-lora_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kunal89/llama3.2-lora_model with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("kunal89/llama3.2-lora_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download adapter_model.safetensors from kunal89/llama3.2-lora_model: direct link, hf CLI and curl.
- Browser
- Download file 210 MB
-
https://huggingface.co/kunal89/llama3.2-lora_model/resolve/46e4950f2f0b46eb4c5ad093f3e0ade8efcebc5f/adapter_model.safetensors
- Command line
-
hf download hf://kunal89/llama3.2-lora_model@46e4950f2f0b46eb4c5ad093f3e0ade8efcebc5f/adapter_model.safetensors
-
curl -L -o adapter_model.safetensors https://huggingface.co/kunal89/llama3.2-lora_model/resolve/46e4950f2f0b46eb4c5ad093f3e0ade8efcebc5f/adapter_model.safetensors
210 MB
- Xet hash:
- 22416b035d1527fc9623e62471eb87ea560f0425a203b8a1da447a35d76e81d7
- Size of remote file:
- 210 MB
- SHA256:
- 2fe2522d944d65c569fe1b6c796eed7a380317dc7e1cecd8150e72426df82311
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.