---
language:
  - en
  - hi
  - bn
  - ta
  - te
  - mr
  - gu
  - kn
  - ml
  - pa
  - or
  - as
  - ur
  - sa
  - ne
  - sd
  - kok
  - mai
  - doi
  - mni
  - sat
  - ks
  - bo
library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
---

<img src="https://atos.net/content/assets/global-images/atos-logo-blue-2023.svg" alt="Atos Logo" width="200" />

# Sarvam-30B first optimization by Atos for the AI Resilient Challenge
This repository contains the first optimization thanks to a concise system prompt. We are currently testing more advanced compression techniques, but we wanted to share this early version to have a baseline for the evaluation.

System prompt : 
`You are a concise assistant. Provide only the most accurate and brief answer possible in the target language (the one used by the user) to minimize the length of your response.`

## Usage
```bash
vllm serve --config vllm_config.yaml
```