Instructions to use bziemba/M3-quantized-qlora-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bziemba/M3-quantized-qlora-4bit with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-0.6B-Base") model = PeftModel.from_pretrained(base_model, "bziemba/M3-quantized-qlora-4bit") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from bziemba/M3-quantized-qlora-4bit: direct link, hf CLI and curl.
- Browser
- Download file 5.69 kB
-
https://huggingface.co/bziemba/M3-quantized-qlora-4bit/resolve/main/training_args.bin
- Command line
-
hf download hf://bziemba/M3-quantized-qlora-4bit/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/bziemba/M3-quantized-qlora-4bit/resolve/main/training_args.bin
5.69 kB
- Xet hash:
- 8a907df5c37425f018f47e87aba1808d465038dd76a3be8c4dd8a5972c8fe81b
- Size of remote file:
- 5.69 kB
- SHA256:
- 96b184da18e222205073bc6b39066a554b5bc804f5c15f6acf0000dc9cbd1d4c
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.