Upload folder using huggingface_hub

.gitattributes

@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 beyonder-4x7b-v3.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 beyonder-4x7b-v3.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
 beyonder-4x7b-v3.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+beyonder-4x7b-v3.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,83 @@
+---
+license: cc-by-nc-4.0
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- autoquant
+- gguf
+base_model:
+- mlabonne/AlphaMonarch-7B
+- beowolx/CodeNinja-1.0-OpenChat-7B
+- SanjiWatsuki/Kunoichi-DPO-v2-7B
+- mlabonne/NeuralDaredevil-7B
+---
+
+# Beyonder-4x7B-v3
+
+Beyonder-4x7B-v3 is a Mixure 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)
+
+## 🧩 Configuration
+
+```yaml
+base_model: mlabonne/AlphaMonarch-7B
+experts:
+  - source_model: mlabonne/AlphaMonarch-7B
+    positive_prompts:
+    - "chat"
+    - "assistant"
+    - "tell me"
+    - "explain"
+    - "I want"
+  - source_model: beowolx/CodeNinja-1.0-OpenChat-7B
+    positive_prompts:
+    - "code"
+    - "python"
+    - "javascript"
+    - "programming"
+    - "algorithm"
+  - source_model: SanjiWatsuki/Kunoichi-DPO-v2-7B
+    positive_prompts:
+    - "storywriting"
+    - "write"
+    - "scene"
+    - "story"
+    - "character"
+  - source_model: mlabonne/NeuralDaredevil-7B
+    positive_prompts:
+    - "reason"
+    - "math"
+    - "mathematics"
+    - "solve"
+    - "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"])
+```

beyonder-4x7b-v3.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d36dfe9cdfa82a0b6aeb6dc5f214fb9c98b7425433c9b58cfe2d62932fa3831
+size 19815794656