RDson
/

Llama-3-Peach-Instruct-4x8B-MoE

Text Generation

Mixture of Experts

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

RDson commited on May 21

Commit

b6a7e43

•

1 Parent(s): ae8fe99

Update README.md

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -19,8 +19,9 @@ This is a experimental MoE created using Mergekit from
 * [rombodawg/Llama-3-8B-Instruct-Coder](https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder)
 Evaluation:
-GSM8K (5-shot): 0.6983 ± 0.0126
 Mergekit yaml file:
 ```

 * [rombodawg/Llama-3-8B-Instruct-Coder](https://huggingface.co/rombodawg/Llama-3-8B-Instruct-Coder)
 Evaluation:
+Q4_K_M:
+* GSM8K (5-shot): 0.6983 ± 0.0126
+* GSM8K (8-shot, cot): 0.674 ± 0.0129
 Mergekit yaml file:
 ```