Instructions to use HaroldB/LLama-2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use HaroldB/LLama-2-7B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyPixel/Llama-2-7B-bf16-sharded") model = PeftModel.from_pretrained(base_model, "HaroldB/LLama-2-7B") - Notebooks
- Google Colab
- Kaggle
Download adapter_model.bin from HaroldB/LLama-2-7B: direct link, hf CLI and curl.
- Browser
- Download file 134 MB
-
https://huggingface.co/HaroldB/LLama-2-7B/resolve/main/adapter_model.bin
- Command line
-
hf download hf://HaroldB/LLama-2-7B/adapter_model.bin
-
curl -L -o adapter_model.bin https://huggingface.co/HaroldB/LLama-2-7B/resolve/main/adapter_model.bin
134 MB
- Xet hash:
- f802bfa7ac1e1ae026897db71384b2500be785637039936de5be7a5574a440d8
- Size of remote file:
- 134 MB
- SHA256:
- 6ccd897cd0916935a5496dd9e25f37b57330a7482d39e151e2a95345ee2593e7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.