Update README.md

README.md

@@ -5,25 +5,69 @@ language:
 - fr
 - en
 tags:
-- phi-3
 - french
-- phi-3-3B
 - chocolatine
+datasets:
+- jpacifico/french-orca-dpo-pairs-revised
+pipeline_tag: text-generation
 ---
 
-### Model Description
+### Chocolatine-3B-Instruct-DPO-Revised  
 
-Chocolatine-3B-Instruct-DPO-Revised  
-3.82B params. Window context = 4k tokens   
-DPO fine-tuned of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct)  
+DPO fine-tuned of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) (3.82B params)  
 using the [jpacifico/french-orca-dpo-pairs-revised](https://huggingface.co/datasets/jpacifico/french-orca-dpo-pairs-revised) rlhf dataset.  
 Chocolatine is a general model and can itself be finetuned to be specialized for specific use cases.  
+Window context = 4k tokens  
 
 ![image/jpeg](https://github.com/jpacifico/Chocolatine-LLM/blob/main/Assets/chocolatine_visuel_500x500.png?raw=true)  
 
 ### Evaluation
 
-Benchmarks very soon ^^  
+Submitted on [OpenLLM Leaderboard](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard), results in few days !  
+
+### Evaluation in French
+
+Chocolatine-3B-Instruct-DPO-Revised is outperforming GPT-3.5-Turbo on [mt-bench-french](https://huggingface.co/datasets/bofenghuang/mt-bench-french) by Bofeng Huang,  
+used with [multilingual-mt-bench](https://github.com/Peter-Devine/multilingual_mt_bench)
+
+![image/jpeg](https://github.com/jpacifico/Chocolatine-LLM/blob/main/Assets/results_fr_mt_bench_400x900.png?raw=false)
+
+### Usage
+
+You can run this model my [Colab notebook](https://github.com/jpacifico/Chocolatine-LLM/blob/main/Chocolatine_3B_inference_test_colab.ipynb) 
+
+You can also run this model using the following code:
+
+```python
+import transformers
+from transformers import AutoTokenizer
+
+# Format prompt
+message = [
+    {"role": "system", "content": "You are a helpful assistant chatbot."},
+    {"role": "user", "content": "What is a Large Language Model?"}
+]
+tokenizer = AutoTokenizer.from_pretrained(new_model)
+prompt = tokenizer.apply_chat_template(message, add_generation_prompt=True, tokenize=False)
+
+# Create pipeline
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=new_model,
+    tokenizer=tokenizer
+)
+
+# Generate text
+sequences = pipeline(
+    prompt,
+    do_sample=True,
+    temperature=0.7,
+    top_p=0.9,
+    num_return_sequences=1,
+    max_length=200,
+)
+print(sequences[0]['generated_text'])
+```
 
 ### Limitations