README.md

---
base_model: tencent/Hunyuan-0.5B-Instruct
library_name: mlx
pipeline_tag: text-generation
tags:
- mlx
---

# Hunyuan-0.5B-Instruct-dwq4-mlx

this model comes in Strarbery flavor:

```bash
How many R are in Strawberry

Hunyuan-0.5B-Instruct-dwq4-mlx
<think>
Okay, let's see. The user is asking how many "R" are in "Strawberry." First, I need to remember the spelling of "Strawberry." Let me recall: "Strawberry" is spelled S-T-R-A-R-B-E-R-Y. Let's break it down letter by letter.

Starting with the first letter: S. Then T. Next is R. Then A. Then R again. Then B. Then E. Then R. Then Y. 

So let's list them out: S, T, R, A, R, B, E, R, Y. Now, I need to count the "R" characters. Let's go through each letter:

1. S (no)
2. T (no)
3. R (yes, count 1)
4. A (no)
5. R (yes, count 2)
6. B (no)
7. E (no)
8. R (yes, count 3)
9. Y (no)

So that's three "R"s. Let me double-check to make sure I didn't miss any. "Strawberry" is S-T-R-A-R-B-E-R-Y.

Let's spell it again
```

Right, for the wrong reason

538.516 tok/sec


This model [Hunyuan-0.5B-Instruct-dwq4-mlx](https://huggingface.co/Hunyuan-0.5B-Instruct-dwq4-mlx) was
converted to MLX format from [tencent/Hunyuan-0.5B-Instruct](https://huggingface.co/tencent/Hunyuan-0.5B-Instruct)
using mlx-lm version **0.26.3**.

## Use with mlx

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

```python
from mlx_lm import load, generate

model, tokenizer = load("Hunyuan-0.5B-Instruct-dwq4-mlx")

prompt = "hello"

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

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