gobean
/

autotrain-mixtral-8x7b-orpo-v1-GGUF

Text Generation

Trained with AutoTrain

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

gobean commited on May 6

Commit

4a2f940

•

1 Parent(s): e94747c

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -13,7 +13,7 @@ license_name: other
 license_link: https://huggingface.co/abhishek/autotrain-mixtral-8x7b-orpo-v1
 ---
-gobean: quants to q4_0, q5_0, q8_0 - the favorites for Mixtrals.
 # - Original Model Card -
 https://huggingface.co/abhishek/autotrain-mixtral-8x7b-orpo-v1

 license_link: https://huggingface.co/abhishek/autotrain-mixtral-8x7b-orpo-v1
 ---
+gobean: quants to q4_0, q5_0, q8_0 - the favorites for Mixtrals. Manually set EOS token to 2, llama.cpp has a bug.
 # - Original Model Card -
 https://huggingface.co/abhishek/autotrain-mixtral-8x7b-orpo-v1