Hugging Face's logo

Lugha-Llama
/
Lugha-Llama-8B-wura_edu

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Inference Endpoints
Model card Files Community
Happyb commited on
Commit
c45e3d4
·
verified ·
1 Parent(s): 8f65f6e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -35,9 +35,12 @@ Contact `{happy.buzaaba@, awettig@cs}princeton.edu`
35
 
36
 
37
  Our main result
38
- ![main_result.png](https://cdn-uploads.huggingface.co/production/uploads/62a8501e1c396da5716cfca2/QFWcWiDKNPEMRSbkakBSH.png)
39
 
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
 
 
35
 
36
 
37
  Our main result
 
38
 
39
+ ![main_result.png](https://cdn-uploads.huggingface.co/production/uploads/62a8501e1c396da5716cfca2/MZw0c4TAnRPYNVdhru7Uo.png)
40
+
41
+ <p align="center">
42
+ <em>Performance of Lugha-Llama models and baselines on <a href="https://arxiv.org/abs/2406.03368"> [IrokoBench]</a>. Languages in italic
43
  are not present in the continual pre-training data. †: We exclude the high-resource languages English (eng) and French (fra) from the average,
44
+ as they would otherwise skew the results due to strong English base models.</em>
45
+ </p>
46