Alsebay
/

L3-8B-SMaid-v0.3

Text Generation

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

Alsebay commited on Jun 23

Commit

268f759

•

1 Parent(s): eb2e4b9

Update README.md

Files changed (1) hide show

README.md +3 -0

README.md CHANGED Viewed

@@ -10,6 +10,9 @@ tags:
 ---
 <img src="https://huggingface.co/Alsebay/L3-8B-SMaid-v0.3/resolve/main/cover/cover.png" alt="img" style="width: 60%; min-width: 120px; height:80%; min-height: 200px; max-width:360px; max-height:600px; display: block">
 # Update: Both version have different presents (settings) to work well
 Overall:

 ---
 <img src="https://huggingface.co/Alsebay/L3-8B-SMaid-v0.3/resolve/main/cover/cover.png" alt="img" style="width: 60%; min-width: 120px; height:80%; min-height: 200px; max-width:360px; max-height:600px; display: block">
+> [!IMPORTANT]
+> This model is wrongly using smaug-bpe pretokenizer during the merge (Mergekit uses smaug-bpe by default for llama-3 merges). So the quality of the model is worse than expected. Still usable with transformers loader.
 # Update: Both version have different presents (settings) to work well
 Overall: