Instructions to use davisrbr/math-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use davisrbr/math-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("ISTA-DASLab/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16") model = PeftModel.from_pretrained(base_model, "davisrbr/math-lora") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from davisrbr/math-lora: direct link, hf CLI and curl.
- Browser
- Download file 5.18 kB
-
https://huggingface.co/davisrbr/math-lora/resolve/main/training_args.bin
- Command line
-
hf download hf://davisrbr/math-lora/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/davisrbr/math-lora/resolve/main/training_args.bin
5.18 kB
- Xet hash:
- d048afe9186d9d2ade3eafda322c44b16a1b10b138ce6214d8eedb8e22ebceef
- Size of remote file:
- 5.18 kB
- SHA256:
- 222b5a3aebccf46c6252f469180d59f06f801f667a1e0d747a680d0a72a218de
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.