Instructions to use k1h0/codellama-7b-ia3-java with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use k1h0/codellama-7b-ia3-java with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("codellama/CodeLlama-7b-hf") model = PeftModel.from_pretrained(base_model, "k1h0/codellama-7b-ia3-java") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-92/training_args.bin from k1h0/codellama-7b-ia3-java: direct link, hf CLI and curl.
- Browser
- Download file 6.9 kB
-
https://huggingface.co/k1h0/codellama-7b-ia3-java/resolve/main/checkpoint-92/training_args.bin
- Command line
-
hf download hf://k1h0/codellama-7b-ia3-java/checkpoint-92/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/k1h0/codellama-7b-ia3-java/resolve/main/checkpoint-92/training_args.bin
6.9 kB
- Xet hash:
- 92431818aba537590992144d7126970ad2765214fe2da8940a7649c9f6effb57
- Size of remote file:
- 6.9 kB
- SHA256:
- fe3ad07bec52bf4960a7d52905afa8030e9a00ae6db6071e0ce0e5a9773ceba2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.