Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,39 @@
+---
+language:
+- ru
+datasets:
+- IlyaGusev/saiga_scored
+- IlyaGusev/saiga_preferences
+license: other
+license_name: yandexgpt-5-lite-8b-pretrain
+license_link: LICENSE
+base_model: IlyaGusev/saiga_yandexgpt_8b
+tags:
+- mlx
+---
+
+# steamdroid/saiga_yandexgpt_8b-mlx-8Bit
+
+The Model [steamdroid/saiga_yandexgpt_8b-mlx-8Bit](https://huggingface.co/steamdroid/saiga_yandexgpt_8b-mlx-8Bit) was converted to MLX format from [IlyaGusev/saiga_yandexgpt_8b](https://huggingface.co/IlyaGusev/saiga_yandexgpt_8b) using mlx-lm version **0.26.3**.
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("steamdroid/saiga_yandexgpt_8b-mlx-8Bit")
+
+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)
+```