Instructions to use smangrul/starcoder-3b-hugcoder-loftq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use smangrul/starcoder-3b-hugcoder-loftq with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("bigcode/starcoder2-3b") model = PeftModel.from_pretrained(base_model, "smangrul/starcoder-3b-hugcoder-loftq") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from smangrul/starcoder-3b-hugcoder-loftq: direct link, hf CLI and curl.
- Browser
- Download file 4.98 kB
-
https://huggingface.co/smangrul/starcoder-3b-hugcoder-loftq/resolve/main/training_args.bin
- Command line
-
hf download hf://smangrul/starcoder-3b-hugcoder-loftq/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/smangrul/starcoder-3b-hugcoder-loftq/resolve/main/training_args.bin
4.98 kB
- Xet hash:
- e40951c901748bbc1396a025aeb5133eefda2c08d8976c22875fbde4f62894d9
- Size of remote file:
- 4.98 kB
- SHA256:
- 5fcc334455a08f5854790649e4fcfd1392321eb828901b6bd398dd2a6c65d676
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.