Update README.md

README.md

@@ -7,14 +7,14 @@ license: apache-2.0
 pipeline_tag: text2text-generation
 ---
 
-# Oolel: A High-Performing Open LLM for Wolof
+# Oolel-Small: On-device AI for Wolof with a Lightweight Language Model
 
 
-Despite numerous open-source innovations in large language models, African languages have remained underrepresented.
+<div style="text-align: center;">
+    <video controls autoplay width="300" height="80" src="https://cdn-uploads.huggingface.co/production/uploads/62e335bbf15e7fce909fe5d4/LAnuFGdmAHEJvsiqtwbtg.mp4"></video>
+</div>
 
-**Soynade Research** is transforming this landscape with Oolel, the first open-source language model for Wolof.
-
-Built on the **Qwen 2.5** architecture, Oolel combines state-of-the-art AI technology with deep Wolof linguistic expertise. With careful high-quality curated data, we trained and optimized Oolel for the following tasks:
+We optimized a small Wolof language model to run on edge devices, such as an iPhone 12. Oolel combines state-of-the-art AI technology with deep Wolof linguistic expertise. With careful high-quality curated data, we trained and optimized Oolel for the simple general tasks:
 
 - **RAG** supporting Wolof queries with English, French, or Wolof context.
 - **Bidirectional translation between English and Wolof**
@@ -29,7 +29,7 @@ Built on the **Qwen 2.5** architecture, Oolel combines state-of-the-art AI techn
 
 **!!! It's important to add your system prompt !!!**
 
-Here provides a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.
+Here is a code snippet with apply_chat_template to show you how to load the tokenizer and model and how to generate contents.
 ```python
 
 from transformers import AutoModelForCausalLM, AutoTokenizer