silx-ai
/

Quasar-40B

Model card Files Files and versions

eyad-silx commited on Sep 9

Commit

ab5ae5f

·

verified ·

1 Parent(s): aa27468

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ These enhancements make Quasar-40B ideal for research, production deployment, an
 - **Base Model**: Kwai-Klear/Klear-46B-A2.5B-Base
 - **Architecture**: Mixture of Experts (MoE) Transformer
-- **Model Type**: Quasar (renamed and enhanced from Klear)
 - **Pretraining Data**: 22 trillion tokens from diverse text sources
 - **Key Enhancements**:
   - Increased number of experts per token

 - **Base Model**: Kwai-Klear/Klear-46B-A2.5B-Base
 - **Architecture**: Mixture of Experts (MoE) Transformer
+- **Model Type**: Quasar
 - **Pretraining Data**: 22 trillion tokens from diverse text sources
 - **Key Enhancements**:
   - Increased number of experts per token