Hugging Face's logo

Lugha-Llama
/
Lugha-Llama-8B-wura_math

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Community
Happyb commited on
Commit
d92b6a6
·
verified ·
1 Parent(s): b4cdd00

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +4 -0
README.md CHANGED
@@ -37,3 +37,7 @@ Contact `{happy.buzaaba@, awettig@cs}princeton.edu`
37
  Our main result
38
 
39
  ![main_result.png](https://cdn-uploads.huggingface.co/production/uploads/62a8501e1c396da5716cfca2/uCwycVoV5dNj-DbjJv9vL.png)
 
 
 
 
 
37
  Our main result
38
 
39
  ![main_result.png](https://cdn-uploads.huggingface.co/production/uploads/62a8501e1c396da5716cfca2/uCwycVoV5dNj-DbjJv9vL.png)
40
+ *Performance of Lugha-Llama models and baselines on IrokoBench [Adelani et al., 2024](https://arxiv.org/abs/2406.03368). Languages in italic
41
+ are not present in the continual pre-training data. †: We exclude the high-resource languages English (eng) and French (fra) from the average,
42
+ as they would otherwise skew the results due to strong English base models.*
43
+