fpaupier commited on
Commit
b058215
·
verified ·
1 Parent(s): 8917f98

Address discrepancies in the languages supported by the Mistral Small 3.1 2503

Browse files

Hi @mistral-ai

The language listed as supported by the Mistral Small 3.1 2503 - both base and instruct version seem to be inconsistent on different model cards provider. This makes it harder to get a comprehensive picture of what you support and is likely to limit adoption (people often search for language supported in their model).
Example, if I only take Dutch and Finnish:
- on the Mistral website release page https://mistral.ai/news/mistral-small-3-1 I see no information on language supported,
- on this HF model card, 24 languages are listed, not Dutch nor Finnish
- on the Kaggle model card - also published by the Mistral org https://www.kaggle.com/models/mistral-ai/mistral-small-3.1/ Dutch and Finnish are mentioned
- On the GCP Vertex doc - https://console.cloud.google.com/vertex-ai/publishers/mistralai/model-garden/mistral-small-2503?invt=Abt7lA — lots of languages are listed with among others, Dutch and Finnish.
See screenshot from GCP below.

![Screenshot 2025-04-05 at 11.26.03.png](https://cdn-uploads.huggingface.co/production/uploads/62739810a512a506233f3a12/xPqZho2RjA523-_8PvVS5.png)


@mgoin I propose a PR to update our supported model list on the HF model card since it’s the go to truth source to compare model supported. If relevant for you, I propose we also update this card on the base model of the small 3.1 2503.

Thanks for sharing the model, really impressed by its performance. Bonus ask; could you share a percentage of language break down in your train set (pre training)?

Files changed (1) hide show
  1. README.md +14 -0
README.md CHANGED
@@ -24,6 +24,20 @@ language:
24
  - vi
25
  - hi
26
  - bn
 
 
 
 
 
 
 
 
 
 
 
 
 
 
27
  license: apache-2.0
28
  library_name: vllm
29
  inference: false
 
24
  - vi
25
  - hi
26
  - bn
27
+ - nl
28
+ - fi
29
+ - ur
30
+ - he
31
+ - br
32
+ - th
33
+ - ca
34
+ - gu
35
+ - kn
36
+ - pa
37
+ - hr
38
+ - da
39
+ - el
40
+ - 'no'
41
  license: apache-2.0
42
  library_name: vllm
43
  inference: false