Update README.md

README.md

@@ -32,7 +32,27 @@ It can be used on a CPU device, compatible with llama.cpp and LM Studio
 
 ### Usage
 
-Test notebook coming soon,  follow me so as not to miss the updates ^^
+```python
+
+model_id = "jpacifico/French-Alpaca-Llama3-8B-Instruct-v1.0"
+model = AutoModelForCausalLM.from_pretrained(model_id, quantization_config=bnb_config, device_map={"":0})
+tokenizer = AutoTokenizer.from_pretrained(model_id, add_eos_token=True, padding_side='left')
+streamer = TextStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens=True)
+
+def stream_frenchalpaca(user_prompt):
+    runtimeFlag = "cuda:0"
+    system_prompt = 'Tu trouveras ci-dessous une instruction qui décrit une tâche. Rédige une réponse qui complète de manière appropriée la demande.\n\n'
+    B_INST, E_INST = "### Instruction:\n", "### Response:\n"
+    prompt = f"{system_prompt}{B_INST}{user_prompt.strip()}\n\n{E_INST}"
+    inputs = tokenizer([prompt], return_tensors="pt").to(runtimeFlag)
+    streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    _ = model.generate(**inputs, streamer=streamer, max_new_tokens=500)
+
+stream_frenchalpaca("your prompt here")
+```
+
+Colab Notebook available on my Github:  
+https://github.com/jpacifico/French-Alpaca/blob/main/French_Alpaca_Llama3_inference_test_colab.ipynb
 
 ### Limitations