README.md

---
library_name: transformers
language:
- bn
- en
- gu
- hi
- kn
- ml
- mr
- or
- pa
- ta
- te
base_model: sarvamai/sarvam-1
tags:
- mlx
---

# mlx-community/sarvam-1-4bit

The Model [mlx-community/sarvam-1-4bit](https://huggingface.co/mlx-community/sarvam-1-4bit) was converted to MLX format from [sarvamai/sarvam-1](https://huggingface.co/sarvamai/sarvam-1) using mlx-lm version **0.19.1**.

## Use with mlx

```bash
pip install mlx-lm
```

```python
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/sarvam-1-4bit")

prompt="hello"

if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
    messages = [{"role": "user", "content": prompt}]
    prompt = tokenizer.apply_chat_template(
        messages, tokenize=False, add_generation_prompt=True
    )

response = generate(model, tokenizer, prompt=prompt, verbose=True)
```