bartowski
/

Mistral-7B-codealpaca-lora-exl2

Model card Files Files and versions

bartowski commited on Oct 28, 2023

Commit

eeb4acf

·

1 Parent(s): d436c9e

Update README.md

Files changed (1) hide show

README.md +5 -0

README.md CHANGED Viewed

	@@ -1,2 +1,7 @@





1
2	<a href="base_quant_repo_url/tree/8.0">8.0 bits per weight</a>

+## Exllama v2 Quantization of Mistral-7B-codealpaca-lora
+Conversion done using evol-codealpaca-v1.parquet as calibration dataset.
+Original model: https://huggingface.co/Nondzu/Mistral-7B-codealpaca-lora
 <a href="base_quant_repo_url/tree/8.0">8.0 bits per weight</a>