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

# GritLM-7B-vllm

> Reference GritLM-7B-vllm checkpoint and architecture details for NeMo AutoModel, with model-family information, setup guidance, and upstream resources.

[GritLM](https://github.com/ContextualAI/gritlm) (Generative Representational Instruction Tuning) is a unified model that performs both generative language modeling and text embedding in a single model, from Parasail AI.

Use this page as a checkpoint and architecture reference. Set up NeMo AutoModel with the
[latest container](https://catalog.ngc.nvidia.com/orgs/nvidia/containers/nemo-automodel) or follow the
[installation instructions](/get-started/installation).

## Model Reference

### Model Architecture

| Property                  | Value                                             |
| ------------------------- | ------------------------------------------------- |
| Task                      | Text Generation + Embedding                       |
| Architecture              | `GritLM`                                          |
| Parameters                | 7B                                                |
| Hugging Face Organization | [parasail-ai](https://huggingface.co/parasail-ai) |

### Available Models

| Model          | HF ID                                                                             |
| -------------- | --------------------------------------------------------------------------------- |
| GritLM 7B vllm | [`parasail-ai/GritLM-7B-vllm`](https://huggingface.co/parasail-ai/GritLM-7B-vllm) |

## Related Resources

* [LLM Fine-Tuning Guide](/recipes-e2e-examples/sft-peft)