Update README.md

README.md

@@ -1,7 +1,41 @@
 ---
-language: en
+license: mit
+library_name: mlx
 pipeline_tag: text-generation
 tags:
+- transformers
 - mlx
-library_name: mlx
+base_model: meituan-longcat/LongCat-Flash-Thinking-2601
 ---
+
+# mlx-community/LongCat-Flash-Thinking-2601-4bit
+
+This model [mlx-community/LongCat-Flash-Thinking-2601-4bit](https://huggingface.co/mlx-community/LongCat-Flash-Thinking-2601-4bit) was
+converted to MLX format from [meituan-longcat/LongCat-Flash-Thinking-2601](https://huggingface.co/meituan-longcat/LongCat-Flash-Thinking-2601)
+using mlx-lm version **0.30.2**.
+
+## Warning
+
+This model is not yet fully compatible with MLX-LM beyond 8192 tokens, but you can track its progress [here](https://github.com/ml-explore/mlx-lm/pull/768) or use [this branch](https://github.com/kernelpool/mlx-lm/tree/longcat-flash) to test it.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/LongCat-Flash-Thinking-2601-4bit")
+
+prompt = "hello"
+
+if tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, add_generation_prompt=True, return_dict=False,
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```