Update README.md

README.md

@@ -5,8 +5,6 @@ language:
 - fr
 - en
 tags:
-- pretrained
-- llama-3
 - openllm-france
 datasets:
 - cmh/alpaca_data_cleaned_fr_52k
@@ -20,11 +18,11 @@ datasets:
 base_model:
 - OpenLLM-France/Lucie-7B
 widget:
-  - text: |-
-      Quelle est la capitale de l'Espagne ? Madrid.
-      Quelle est la capitale de la France ?
-    example_title: Capital cities in French
-    group: 1-shot Question Answering
+- text: |-
+    Quelle est la capitale de l'Espagne ? Madrid.
+    Quelle est la capitale de la France ?
+  example_title: Capital cities in French
+  group: 1-shot Question Answering
 training_progress:
   context_length: 32000
 ---
@@ -57,7 +55,7 @@ Note that this instruction training is light and is meant to allow Lucie to prod
 
 Due to its size, Lucie-7B is limited in the information that it can memorize; its ability to produce correct answers could be improved by implementing the model in a retrieval augmented generation pipeline.
 
-While Lucie-7B-Instruct is trained on sequences of 4096 tokens, its base model, Lucie-7B has a context size of 32K tokens. Based on Needle-in-a-haystack evaluations, Lucie-7B-Instruct maintains the capacity of the base model to handle 32K-size context windows. 
+While Lucie-7B-Instruct is trained on sequences of 4096 tokens, its base model, Lucie-7B has a context size of 32K tokens. Based on Needle-in-a-haystack evaluations, Lucie-7B-Instruct-v1.1 has a context window size of 22K tokens. This window could be increasd by fine-tuning on longer data samples.  
 
 
 ## Training details
@@ -232,4 +230,4 @@ Finally, we thank the entire OpenLLM-France community, whose members have helped
 
 ## Contact
 
-contact@openllm-france.fr
+contact@openllm-france.fr