Update README.md

README.md

@@ -16,28 +16,59 @@ These are pre-converted weights and ready to be used in the example scripts.
 
 # Quick start for LLMs
 
-Check out the MLX examples repo:
+Install `mlx-lm`:
 
 ```
-git clone [email protected]:ml-explore/mlx-examples.git
-cd mlx-examples/hf_llm
+pip install mlx-lm
 ```
 
-Install the requirements:
+You can use `mlx-lm` from the command line. For example:
 
 ```
-pip install -r requirements.txt
+python -m mlx_lm.generate --model mistralai/Mistral-7B-v0.1 --prompt "hello"
 ```
 
-Generate:
+This will download a Mistral 7B model from the Hugging Face Hub and generate
+text using the given prompt. 
+
+For a full list of options run:
+
+```
+python -m mlx_lm.generate --help
+```
+
+To quantize a model from the command line run:
+
+```
+python -m mlx_lm.convert --hf-path mistralai/Mistral-7B-v0.1 -q 
+```
+
+For more options run:
 
 ```
-python generate.py --hf-path mistralai/Mistral-7B-v0.1 --prompt "hello"
+python -m mlx_lm.convert --help
 ```
 
-To upload a new model (for example a 4-bit quantized Mistral-7B), do:
+You can upload new models to Hugging Face by specifying `--upload-repo` to
+`convert`. For example, to upload a quantized Mistral-7B model to the 
+[MLX Hugging Face community](https://huggingface.co/mlx-community) you can do:
 
 ```
-python convert.py --hf-path mistralai/Mistral-7B-v0.1 -q --upload-name mistral-v0.1-4bit
+python -m mlx_lm.convert \
+    --hf-path mistralai/Mistral-7B-v0.1 \
+    -q \
+    --upload-repo mlx-community/my-4bit-mistral
 ```
 
+For more details on the API checkout the full [README](https://github.com/ml-explore/mlx-examples/tree/main/llms)
+
+
+### Other Examples:
+
+For more examples, visit the [MLX Examples](https://github.com/ml-explore/mlx-examples) repo. The repo includes examples of:
+
+- Parameter efficient fine tuning with LoRA
+- Speech recognition with Whisper
+- Image generation with Stable Diffusion
+
+  and many other examples of different machine learning applications and algorithms.