convaiinnovations
/

hindi-causal-lm

Text Generation

Model card Files Files and versions Community

convaiinnovations commited on 11 days ago

Commit

9ec04da

·

verified ·

1 Parent(s): c8f0b46

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -24,7 +24,7 @@ A Hindi language generation model with the following specifications:
 - **Key-value heads**: 4 (using grouped-query attention)
 - **Position encoding**: Rotary Position Embeddings (RoPE)
 - **Vocabulary size**: 16000
-- **Parameters**: ~74.1M
 - **Context window**: 512 tokens
 - **Trained on**: Large corpus of Hindi text

 - **Key-value heads**: 4 (using grouped-query attention)
 - **Position encoding**: Rotary Position Embeddings (RoPE)
 - **Vocabulary size**: 16000
+- **Parameters**: ~100M
 - **Context window**: 512 tokens
 - **Trained on**: Large corpus of Hindi text