README.md

---
base_model: togethercomputer/Tev1-4B-experimental
pipeline_tag: text-generation
library_name: mlx
tags:
- together-ai
- qwen3.5
- decision-model
- experimental
- mlx
---

# gavinmroy/Tev1-4B-experimental-mlx-4bit

This model [gavinmroy/Tev1-4B-experimental-mlx-4bit](https://huggingface.co/gavinmroy/Tev1-4B-experimental-mlx-4bit) was
converted to MLX format from [togethercomputer/Tev1-4B-experimental](https://huggingface.co/togethercomputer/Tev1-4B-experimental)
using mlx-lm version **0.31.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("gavinmroy/Tev1-4B-experimental-mlx-4bit")

prompt = "hello"

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

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