Create README.md

README.md

@@ -0,0 +1,58 @@
+---
+language:
+- en
+base_model: louisbrulenaudet/Pearl-3x7B
+library_name: mlx
+tags:
+- moe
+- frankenmoe
+- merge
+- mergekit
+- lazymergekit
+- dvilasuero/DistilabelBeagle14-7B
+- beowolx/CodeNinja-1.0-OpenChat-7B
+- WizardLM/WizardMath-7B-V1.1
+- Maths
+- Code
+- Python
+pipeline_tag: text-generation
+license: apache-2.0
+---
+
+<center><img src='https://i.imgur.com/dU9dUh0.png' width='500px'></center>
+
+# mlx-community/Pearl-3x7B
+
+This model was converted to MLX format from [`louisbrulenaudet/Pearl-3x7B`]() using mlx-vlm version **0.16.1**.
+Refer to the [original model card](louisbrulenaudet/Pearl-3x7B) for more details on the model.
+
+## Use with mlx
+
+```bash
+pip install -U mlx-vlm
+python -m mlx_vlm.generate --model  mlx-community/Pearl-3x7B --max-tokens 100 --temp 0.0
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/Pearl-3x7B")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```
+
+## Citing & Authors
+
+If you use this code in your research, please use the following BibTeX entry.
+
+```BibTeX
+@misc{louisbrulenaudet2024,
+  author =       {Louis Brulé Naudet},
+  title =        {Pearl-3x7B, an xtraordinary Mixture of Experts (MoE) for data science},
+  year =         {2024}
+  howpublished = {\url{https://huggingface.co/mlx-community/Pearl-3x7B}},
+}
+```
+
+## Feedback
+
+If you have any feedback, please reach out at [[email protected]](mailto:[email protected]).