Update README.md

README.md

@@ -34,7 +34,8 @@ model-index:
 ---
 
 # lang-uk/dragoman-4bit
-This model was converted to MLX format from [`lang-uk/dragoman`]() using mlx-lm version **0.4.0**.
+This model was converted to MLX format from the [`lang-uk/dragoman`](https://huggingface.co/lang-uk/dragoman) adapter fused into the [`mistralai/Mistral-7b-v0.1`](https://huggingface.co/mistralai/Mistral-7B-v0.1)
+base model and quantized into 4 bits using mlx-lm version **0.4.0**.
 Refer to the [original model card](https://huggingface.co/lang-uk/dragoman) for more details on the model.
 ## Use with mlx
 
@@ -48,3 +49,9 @@ from mlx_lm import load, generate
 model, tokenizer = load("lang-uk/dragoman-4bit")
 response = generate(model, tokenizer, prompt="hello", verbose=True)
 ```
+
+Or use from your shell:
+
+```console
+python -m mlx_lm.generate --model lang-uk/dragoman-4bit --prompt '[INST] who holds this neighborhood? [/INST]' --temp 0 --max-tokens 100
+```