Update README.md

README.md

@@ -72,7 +72,7 @@ The model architecture and hyperparameters are the same as for [Lucie-7B](https:
 ### Test with ollama
 
 * Download and install [Ollama](https://ollama.com/download)
-* Download the [GGUF model](https://huggingface.co/OpenLLM-France/Lucie-7B-Instruct-v1/resolve/main/Lucie-7B-q4_k_m.gguf)
+* Download the [GGUF model](https://huggingface.co/OpenLLM-France/Lucie-7B-Instruct/resolve/main/Lucie-7B-q4_k_m.gguf)
 * Copy the [`Modelfile`](Modelfile), adpating if necessary the path to the GGUF file (line starting with `FROM`).
 * Run in a shell:
     * `ollama create -f Modelfile Lucie`
@@ -101,7 +101,7 @@ docker run --runtime nvidia --gpus=all \
     -p 8000:8000 \
     --ipc=host \
     vllm/vllm-openai:latest \
-    --model OpenLLM-France/Lucie-7B-Instruct-v1
+    --model OpenLLM-France/Lucie-7B-Instruct
 ```
 
 #### 2. Test using OpenAI Client in Python
@@ -119,7 +119,7 @@ content = "Hello Lucie"
 
 # Generate a response
 chat_response = client.chat.completions.create(
-    model="OpenLLM-France/Lucie-7B-Instruct-v1",
+    model="OpenLLM-France/Lucie-7B-Instruct",
     messages=[
         {"role": "user", "content": content}
     ],