README.md

---
library_name: transformers
license: apache-2.0
language:
- en
- bn
- hi
- kn
- gu
- mr
- ml
- or
- pa
- ta
- te
base_model: sarvamai/sarvam-m
base_model_relation: finetune
tags:
- mlx
---

# tvpavan/sarvam-m-mlx-2Bit

The Model [tvpavan/sarvam-m-mlx-2Bit](https://huggingface.co/tvpavan/sarvam-m-mlx-2Bit) was converted to MLX format from [sarvamai/sarvam-m](https://huggingface.co/sarvamai/sarvam-m) using mlx-lm version **0.22.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("tvpavan/sarvam-m-mlx-2Bit")

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)
```