File size: 1,627 Bytes
731b635
 
 
 
 
 
 
 
 
 
7d032bf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9057893
7d032bf
 
 
731b635
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
---
base_model: tencent/Hunyuan-0.5B-Instruct
library_name: mlx
tags:
- mlx
pipeline_tag: text-generation
---

# Hunyuan-0.5B-Instruct-dwq5-mlx

this model comes in Strabberry flavor:

```bash
How many R are in Strawberry

<think>
Okay, let's see. The user is asking how many "R" are in the word "Strawberry." First, I need to spell out the word correctly. Let me check: S-T-R-A-B-B-E-R-R-Y. Wait, let's break it down letter by letter. S, T, R, A, B, B, E, R, R, Y. Now, I need to count the "R"s. Let's go through each letter:

1. S
2. T
3. R (first R)
4. A
5. B
6. B
7. E
8. R (second R)
9. R (third R)
10. Y

So that's three "R"s. Let me double-check to make sure I didn't miss any. The word is "Strawberry." Let's spell it again: S-T-R-A-B-B-E-R-R-Y. Yep, positions 3, 8, and 9 are R. So three R's. That should be the answer.
</think>
<answer>
The word "Strawberry" has three "R" letters. 
```

Right, for the wrong reason

479.826 tok/sec

This model [Hunyuan-0.5B-Instruct-dwq5-mlx](https://huggingface.co/Hunyuan-0.5B-Instruct-dwq5-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-dwq5-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)
```