> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://fr.nvidia-localization.ferndocs.com/fr/nemo/rl/latest/nemo-rl-package-info/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://fr.nvidia-localization.ferndocs.com/_mcp/server.

# nemo\_rl.package\_info

## Contenu du Module

### Données

`MAJOR`
`MINOR`
`PATCH`
`PRE_RELEASE`
`VERSION`
`__shortversion__`
`__version__`
`__package_name__`
`__contact_names__`
`__contact_emails__`
`__homepage__`
`__repository_url__`
`__download_url__`
`__description__`
`__license__`
`__keywords__`

### API

```python
nemo_rl.package_info.MAJOR
```

**Valeur**: `0`

```python
nemo_rl.package_info.MINOR
```

**Valeur**: `4`

```python
nemo_rl.package_info.PATCH
```

**Valeur**: `0`

```python
nemo_rl.package_info.PRE_RELEASE
```

**Valeur**: `rc0`

```python
nemo_rl.package_info.VERSION
```

**Valeur**: `()`

```python
nemo_rl.package_info.__shortversion__
```

**Valeur**: `join(...)`

```python
nemo_rl.package_info.__version__
```

**Valeur**: `None`

```python
nemo_rl.package_info.__package_name__
```

**Valeur**: `nemo_rl`

```python
nemo_rl.package_info.__contact_names__
```

**Valeur**: `NVIDIA`

```python
nemo_rl.package_info.__contact_emails__
```

**Valeur**: `nemo-tookit@nvidia.com`

```python
nemo_rl.package_info.__homepage__
```

**Valeur**: `https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/stable/`

```python
nemo_rl.package_info.__repository_url__
```

**Valeur**: `https://github.com/NVIDIA-NeMo/RL`

```python
nemo_rl.package_info.__download_url__
```

**Valeur**: `https://github.com/NVIDIA-NeMo/RL/releases`

```python
nemo_rl.package_info.__description__
```

**Valeur**: `NeMo-RL - une boîte à outils pour l'alignement de modèles`

```python
nemo_rl.package_info.__license__
```

**Valeur**: `Apache2`

```python
nemo_rl.package_info.__keywords__
```

**Valeur**: `apprentissage profond, apprentissage automatique, gpu, NLP, NeMo, nvidia, pytorch, torch, langue, apprentissage par renforcement, RLHF, modélisation de préférences, SteerLM, DPO`