Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,37 @@
+---
+language:
+- ru
+datasets:
+- IlyaGusev/saiga_scored
+- IlyaGusev/saiga_preferences
+license: apache-2.0
+tags:
+- mlx
+base_model: IlyaGusev/saiga_nemo_12b
+---
+
+# fengpeisheng1/saiga_nemo_12b-mlx-3Bit
+
+The Model [fengpeisheng1/saiga_nemo_12b-mlx-3Bit](https://huggingface.co/fengpeisheng1/saiga_nemo_12b-mlx-3Bit) was converted to MLX format from [IlyaGusev/saiga_nemo_12b](https://huggingface.co/IlyaGusev/saiga_nemo_12b) using mlx-lm version **0.22.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("fengpeisheng1/saiga_nemo_12b-mlx-3Bit")
+
+prompt="hello"
+
+if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
+    messages = [{"role": "user", "content": prompt}]
+    prompt = tokenizer.apply_chat_template(
+        messages, tokenize=False, add_generation_prompt=True
+    )
+
+response = generate(model, tokenizer, prompt=prompt, verbose=True)
+```