Update README.md

README.md

@@ -112,20 +112,26 @@ model-index:
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/gFEhcIDSKa3AWpkNfH91q.jpeg)
 
-This is a DPO fine-tune of [mlabonne/Daredevil-8-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated) trained on one epoch of [mlabonne/orpo-dpo-mix-40k](https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k).
-It is an improved version of the abliterated model.
+This is a DPO fine-tune of [mlabonne/Daredevil-8-abliterated](https://huggingface.co/mlabonne/Daredevil-8B-abliterated), trained on one epoch of [mlabonne/orpo-dpo-mix-40k](https://huggingface.co/datasets/mlabonne/orpo-dpo-mix-40k).
+The DPO fine-tuning successfully recovers the performance loss due to the abliteration process, making it an excellent uncensored model.
 
 ## 🔎 Applications
 
-This is an uncensored model. You can use it for any application that doesn't require alignment, like role-playing.
+NeuralDaredevil-8B-abliterated performs better than the Instruct model on my tests.
 
-Tested on LM Studio using the "Llama 3" preset.
+You can use it for any application that doesn't require alignment, like role-playing. Tested on LM Studio using the "Llama 3" preset.
+
+## ⚡ Quantization
+
+* **GGUF**: https://huggingface.co/mlabonne/NeuralDaredevil-8B-abliterated-GGUF
 
 ## 🏆 Evaluation
 
 ### Open LLM Leaderboard
 
-TBD.
+NeuralDaredevil-8B is the best-performing uncensored 8B model on the Open LLM Leaderboard (MMLU score).
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/TqTEbSQ7HAE7QTQBSyKoi.png)
 
 ### Nous
 
@@ -141,20 +147,31 @@ Evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoev
 | [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) [📄](https://gist.github.com/mlabonne/8329284d86035e6019edb11eb0933628) | 51.34 | 41.22 | 69.86 | 51.65 | 42.64 |
 | [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) [📄](https://gist.github.com/mlabonne/616b6245137a9cfc4ea80e4c6e55d847) | 45.42 | 31.1 | 69.95 | 43.91 | 36.7 |
 
-
 ## 🌳 Model family tree
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/ekwRGgnjzEOyprT8sEBFt.png)
-# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
-Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_mlabonne__Daredevil-8B-abliterated-dpomix)
-
-|             Metric              |Value|
-|---------------------------------|----:|
-|Avg.                             |72.32|
-|AI2 Reasoning Challenge (25-Shot)|69.28|
-|HellaSwag (10-Shot)              |85.05|
-|MMLU (5-Shot)                    |69.10|
-|TruthfulQA (0-shot)              |60.00|
-|Winogrande (5-shot)              |78.69|
-|GSM8k (5-shot)                   |71.80|
 
+## 💻 Usage
+
+```python
+!pip install -qU transformers accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "mlabonne/Daredevil-8B"
+messages = [{"role": "user", "content": "What is a large language model?"}]
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+```