Instructions to use davisrbr/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use davisrbr/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r16 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/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r16") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from davisrbr/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r16: direct link, hf CLI and curl.
- Browser
- Download file 5.05 kB
-
https://huggingface.co/davisrbr/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r16/resolve/main/training_args.bin
- Command line
-
hf download hf://davisrbr/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r16/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/davisrbr/Meta-Llama-3-8B-Instruct-AQLM-2Bit-1x16-r16/resolve/main/training_args.bin
5.05 kB
- Xet hash:
- 14649664b17ba9d7cc87404fbd7b5368d6d28a121b2c6fba2ed24abfcf47a1f0
- Size of remote file:
- 5.05 kB
- SHA256:
- 11cf7b5119fe8a185915e2014db6310d4cd99da4b7af0e6f905ca47119342911
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.