Update README.md

README.md

@@ -65,7 +65,15 @@ Mistral Nemo is a transformer model, with the following architecture choices:
 | Chinese | 59.0% |
 | Japanese | 59.0% |
 
-## Installation with `mistral_inference`
+## Usage
+
+The model can be used with three different frameworks
+
+- [`mistral_inference`](https://github.com/mistralai/mistral-inference): See [here](#mistral-inference)
+- [`transformers`](https://github.com/huggingface/transformers): See [here](#transformers)
+- [`NeMo`](https://github.com/NVIDIA/NeMo): See [nvidia/Mistral-NeMo-12B-Instruct](https://huggingface.co/nvidia/Mistral-NeMo-12B-Instruct)
+
+#### Install
 
 It is recommended to use `mistralai/Mistral-Nemo-Instruct-2407` with [mistral-inference](https://github.com/mistralai/mistral-inference). For HF transformers code snippets, please keep scrolling.
 
@@ -73,7 +81,7 @@ It is recommended to use `mistralai/Mistral-Nemo-Instruct-2407` with [mistral-in
 pip install mistral_inference
 ```
 
-### Download
+#### Download
 
 ```py
 from huggingface_hub import snapshot_download
@@ -85,7 +93,7 @@ mistral_models_path.mkdir(parents=True, exist_ok=True)
 snapshot_download(repo_id="mistralai/Mistral-Nemo-Instruct-2407", allow_patterns=["params.json", "consolidated.safetensors", "tekken.json"], local_dir=mistral_models_path)
 ```
 
-### Chat
+#### Chat
 
 After installing `mistral_inference`, a `mistral-chat` CLI command should be available in your environment. You can chat with the model using
 
@@ -98,7 +106,7 @@ mistral-chat $HOME/mistral_models/Nemo-Instruct --instruct --max_tokens 256 --te
 How expensive would it be to ask a window cleaner to clean all windows in Paris. Make a reasonable guess in US Dollar.
 ```
 
-### Instruct following
+#### Instruct following
 
 ```py
 from mistral_inference.transformer import Transformer
@@ -123,7 +131,7 @@ result = tokenizer.decode(out_tokens[0])
 print(result)
 ```
 
-### Function calling
+#### Function calling
 
 ```py
 from mistral_common.protocol.instruct.tool_calls import Function, Tool
@@ -175,7 +183,7 @@ result = tokenizer.decode(out_tokens[0])
 print(result)
 ```
 
-## Generate with `transformers`
+### Transformers
 
 > [!IMPORTANT]
 > NOTE: Until a new release has been made, you need to install transformers from source: