Instructions to use FINGU-AI/QWEN2.5-32B-v3-5400s with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use FINGU-AI/QWEN2.5-32B-v3-5400s with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen2.5-32b-instruct-bnb-4bit") model = PeftModel.from_pretrained(base_model, "FINGU-AI/QWEN2.5-32B-v3-5400s") - Notebooks
- Google Colab
- Kaggle
Download optimizer.pt from FINGU-AI/QWEN2.5-32B-v3-5400s: direct link, hf CLI and curl.
- Browser
- Download file 14.8 GB
-
https://huggingface.co/FINGU-AI/QWEN2.5-32B-v3-5400s/resolve/main/optimizer.pt
- Command line
-
hf download hf://FINGU-AI/QWEN2.5-32B-v3-5400s/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/FINGU-AI/QWEN2.5-32B-v3-5400s/resolve/main/optimizer.pt
14.8 GB
- Xet hash:
- 1b792be936c7f65c2cb39ab3f7f51a10847f1d221569d818ea168a54f3e60108
- Size of remote file:
- 14.8 GB
- SHA256:
- 1a8b1818947861960c9b6c00d70f1c6eebcfefa555812a10a5009330e96382e8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.