Update README.md

README.md

@@ -1,7 +1,43 @@
 ---
-language: en
+library_name: transformers
+model_name: Shisa V2.1 14B
+license: mit
 pipeline_tag: text-generation
+language:
+- ja
+- en
 tags:
 - mlx
-library_name: mlx
+base_model:
+- shisa-ai/shisa-v2.1-unphi4-14b
+datasets:
+- shisa-ai/shisa-v2.1-sharegpt
 ---
+
+# mlx-community/shisa-v2.1-unphi4-14b-mlx-bf16
+
+The Model [mlx-community/shisa-v2.1-unphi4-14b-mlx-bf16](https://huggingface.co/mlx-community/shisa-v2.1-unphi4-14b-mlx-bf16) was converted to MLX format from [shisa-ai/shisa-v2.1-unphi4-14b](https://huggingface.co/shisa-ai/shisa-v2.1-unphi4-14b) using mlx-lm version **0.28.4**.
+
+You can find other similar translation-related MLX model quants for an Apple Mac at https://huggingface.co/bibproj
+
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/shisa-v2.1-unphi4-14b-mlx-bf16")
+
+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)
+```