Instructions to use ulas742/lora-mid with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use ulas742/lora-mid with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B") model = PeftModel.from_pretrained(base_model, "ulas742/lora-mid") - Notebooks
- Google Colab
- Kaggle
Download checkpoint-3000/optimizer.pt from ulas742/lora-mid: direct link, hf CLI and curl.
- Browser
- Download file 85.3 MB
-
https://huggingface.co/ulas742/lora-mid/resolve/main/checkpoint-3000/optimizer.pt
- Command line
-
hf download hf://ulas742/lora-mid/checkpoint-3000/optimizer.pt
-
curl -L -o optimizer.pt https://huggingface.co/ulas742/lora-mid/resolve/main/checkpoint-3000/optimizer.pt
85.3 MB
- Xet hash:
- dc485a6a2ae07604e9b5a153d9c684b0acddedd90f13cb20e25b341d1768053c
- Size of remote file:
- 85.3 MB
- SHA256:
- 2fc5b9e0d5fa3e2a88c699b0c1c541018e0c1bf036d6d3b245669679440a5e6e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.