Instructions to use JesseLiu/llama32-3b-kpath with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use JesseLiu/llama32-3b-kpath with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-3B-Instruct") model = PeftModel.from_pretrained(base_model, "JesseLiu/llama32-3b-kpath") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from JesseLiu/llama32-3b-kpath: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/JesseLiu/llama32-3b-kpath/resolve/main/tokenizer.json
- Command line
-
hf download hf://JesseLiu/llama32-3b-kpath/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/JesseLiu/llama32-3b-kpath/resolve/main/tokenizer.json
17.2 MB
- Xet hash:
- 9890273f24a9286ff5e5b78b608ac7136bdf47c5d9358ecb5b64eea803a59d4a
- Size of remote file:
- 17.2 MB
- SHA256:
- 75f308eab34ebd3e599c8783678020931835ac7bd549b24c6572fe1c0df52b36
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.