Update README.md

README.md

@@ -17,14 +17,16 @@ base_model:
 
 ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/9XVgxKyuXTQVO5mO-EOd4.jpeg)
 
-# 🔮 Beyonder-4x7B-v3
+# 🔮 Beyonder-4x7B-v3 GGUF
 
-Beyonder-4x7B-v3 is an improvement over the popular [Beyonder-4x7B-v2](https://huggingface.co/mlabonne/Beyonder-4x7B-v2). It's a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
+[Beyonder-4x7B-v3](https://huggingface.co/mlabonne/Beyonder-4x7B-v3) is an improvement over the popular [Beyonder-4x7B-v2](https://huggingface.co/mlabonne/Beyonder-4x7B-v2). It's a Mixture of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
 * [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B)
 * [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B)
 * [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B)
 * [mlabonne/NeuralDaredevil-7B](https://huggingface.co/mlabonne/NeuralDaredevil-7B)
 
+Special thanks to [beowolx](https://huggingface.co/beowolx) for making the best Mistral-based code model and to [SanjiWatsuki](https://huggingface.co/SanjiWatsuki) for creating one of the very best RP models.
+
 ## 🔍 Applications
 
 This model uses a context window of 8k. I recommend using it with the Mistral Instruct chat template (works perfectly with LM Studio).
@@ -35,10 +37,16 @@ Thanks to its four experts, it's a well-rounded model, capable of achieving most
 
 ## ⚡ Quantized models
 
+Thanks [bartowski](https://huggingface.co/bartowski) for quantizing this model.
+
 * **GGUF**: https://huggingface.co/mlabonne/Beyonder-4x7B-v3-GGUF
+* **More GGUF**: https://huggingface.co/bartowski/Beyonder-4x7B-v3-GGUF
+* **ExLlamaV2**: https://huggingface.co/bartowski/Beyonder-4x7B-v3-exl2
 
 ## 🏆 Evaluation
 
+This model is not designed to excel in traditional benchmarks, as the code and role-playing models generally do not apply to those contexts. Nonetheless, it performs remarkably well thanks to strong general-purpose experts.
+
 ### Nous
 
 Beyonder-4x7B-v3 is one of the best models on Nous' benchmark suite (evaluation performed using [LLM AutoEval](https://github.com/mlabonne/llm-autoeval)) and significantly outperforms the v2. See the entire leaderboard [here](https://huggingface.co/spaces/mlabonne/Yet_Another_LLM_Leaderboard).
@@ -48,11 +56,21 @@ Beyonder-4x7B-v3 is one of the best models on Nous' benchmark suite (evaluation
 | [mlabonne/AlphaMonarch-7B](https://huggingface.co/mlabonne/AlphaMonarch-7B) [📄](https://gist.github.com/mlabonne/1d33c86824b3a11d2308e36db1ba41c1) | 62.74 | 45.37 | 77.01 | 78.39 | 50.2 |
 | [**mlabonne/Beyonder-4x7B-v3**](https://huggingface.co/mlabonne/Beyonder-4x7B-v3) [📄](https://gist.github.com/mlabonne/3740020807e559f7057c32e85ce42d92) | **61.91** | **45.85** | **76.67** | **74.98** | **50.12** |
 | [mlabonne/NeuralDaredevil-7B](https://huggingface.co/mlabonne/NeuralDaredevil-7B) [📄](https://gist.github.com/mlabonne/cbeb077d1df71cb81c78f742f19f4155) | 59.39 | 45.23 | 76.2 | 67.61 | 48.52 |
+| [SanjiWatsuki/Kunoichi-DPO-v2-7B](https://huggingface.co/SanjiWatsuki/Kunoichi-DPO-v2-7B) [📄](https://gist.github.com/mlabonne/895ff5171e998abfdf2a41a4f9c84450) | 58.29 | 44.79 | 75.05 | 65.68 | 47.65 |
 | [mlabonne/Beyonder-4x7B-v2](https://huggingface.co/mlabonne/Beyonder-4x7B-v2) [📄](https://gist.github.com/mlabonne/f73baa140a510a676242f8a4496d05ca) | 57.13 | 45.29 | 75.95 | 60.86 | 46.4 |
+| [beowolx/CodeNinja-1.0-OpenChat-7B](https://huggingface.co/beowolx/CodeNinja-1.0-OpenChat-7B) [📄](https://gist.github.com/mlabonne/08b5280c221fbd7f98eb27561ae902a3) | 50.35 | 39.98 | 71.77 | 48.73 | 40.92 |
+
+### EQ-Bench
+
+Beyonder-4x7B-v3 is the best 4x7B model on the EQ-Bench leaderboard, outperforming older versions of ChatGPT and Llama-2-70b-chat. It is very close to Mixtral-8x7B-Instruct-v0.1 and Gemini Pro. Thanks [Sam Paech](https://huggingface.co/sam-paech) for running the eval.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/-OSHe2ImrxN8wAREnSZAZ.png)
 
 ### Open LLM Leaderboard
 
-Running...
+It's also a strong performer on the Open LLM Leaderboard, significantly outperforming the v2 model.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/NFRYqzwuy9TB-s-Hy3gRy.png)
 
 ## 🧩 Configuration
 
@@ -89,29 +107,6 @@ experts:
     - "count"
 ```
 
-## 💻 Usage
-
-```python
-!pip install -qU transformers bitsandbytes accelerate
-
-from transformers import AutoTokenizer
-import transformers
-import torch
-
-model = "mlabonne/Beyonder-4x7B-v3"
-
-tokenizer = AutoTokenizer.from_pretrained(model)
-pipeline = transformers.pipeline(
-    "text-generation",
-    model=model,
-    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
-)
-
-messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
-prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
-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"])
-```
-Output:
+## 🌳 Model Family Tree
 
-> A Mixture of Experts (MoE) is a neural network architecture that tackles complex tasks by dividing them into simpler subtasks, delegating each to specialized expert modules. These experts learn to independently handle specific problem aspects. The MoE structure combines their outputs, leveraging their expertise for improved overall performance. This approach promotes modularity, adaptability, and scalability, allowing for better generalization in various applications.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/61b8e2ba285851687028d395/zQi5VgmdqJv6pFaGoQ2AL.png)