Hugging Face's logo

RichardErkhov
/
TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf

GGUF
conversational
Model card Files Community
RichardErkhov commited on
Commit
8c4db41
·
verified ·
1 Parent(s): 05477f8

uploaded readme

Browse files
Files changed (1) hide show
  1. README.md +89 -0
README.md ADDED
@@ -0,0 +1,89 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Quantization made by Richard Erkhov.
2
+
3
+ [Github](https://github.com/RichardErkhov)
4
+
5
+ [Discord](https://discord.gg/pvy7H8DZMG)
6
+
7
+ [Request more models](https://github.com/RichardErkhov/quant_request)
8
+
9
+
10
+ Qwen2.5-Coder-0.5B-Instruct-MLX - GGUF
11
+ - Model creator: https://huggingface.co/TheBlueObserver/
12
+ - Original model: https://huggingface.co/TheBlueObserver/Qwen2.5-Coder-0.5B-Instruct-MLX/
13
+
14
+
15
+ | Name | Quant method | Size |
16
+ | ---- | ---- | ---- |
17
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q2_K.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q2_K.gguf) | Q2_K | 0.32GB |
18
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.IQ3_XS.gguf) | IQ3_XS | 0.32GB |
19
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.IQ3_S.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.IQ3_S.gguf) | IQ3_S | 0.32GB |
20
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K_S.gguf) | Q3_K_S | 0.32GB |
21
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.IQ3_M.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.IQ3_M.gguf) | IQ3_M | 0.32GB |
22
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K.gguf) | Q3_K | 0.33GB |
23
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K_M.gguf) | Q3_K_M | 0.33GB |
24
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q3_K_L.gguf) | Q3_K_L | 0.34GB |
25
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.IQ4_XS.gguf) | IQ4_XS | 0.33GB |
26
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_0.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_0.gguf) | Q4_0 | 0.33GB |
27
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.IQ4_NL.gguf) | IQ4_NL | 0.33GB |
28
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_K_S.gguf) | Q4_K_S | 0.36GB |
29
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_K.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_K.gguf) | Q4_K | 0.37GB |
30
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_K_M.gguf) | Q4_K_M | 0.37GB |
31
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_1.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q4_1.gguf) | Q4_1 | 0.35GB |
32
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_0.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_0.gguf) | Q5_0 | 0.37GB |
33
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_K_S.gguf) | Q5_K_S | 0.38GB |
34
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_K.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_K.gguf) | Q5_K | 0.39GB |
35
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_K_M.gguf) | Q5_K_M | 0.39GB |
36
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_1.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q5_1.gguf) | Q5_1 | 0.39GB |
37
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q6_K.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q6_K.gguf) | Q6_K | 0.47GB |
38
+ | [Qwen2.5-Coder-0.5B-Instruct-MLX.Q8_0.gguf](https://huggingface.co/RichardErkhov/TheBlueObserver_-_Qwen2.5-Coder-0.5B-Instruct-MLX-gguf/blob/main/Qwen2.5-Coder-0.5B-Instruct-MLX.Q8_0.gguf) | Q8_0 | 0.49GB |
39
+
40
+
41
+
42
+
43
+ Original model description:
44
+ ---
45
+ license: apache-2.0
46
+ license_link: https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct/blob/main/LICENSE
47
+ language:
48
+ - en
49
+ base_model: Qwen/Qwen2.5-Coder-0.5B-Instruct
50
+ pipeline_tag: text-generation
51
+ library_name: transformers
52
+ tags:
53
+ - code
54
+ - codeqwen
55
+ - chat
56
+ - qwen
57
+ - qwen-coder
58
+ - mlx
59
+ ---
60
+
61
+ # TheBlueObserver/Qwen2.5-Coder-0.5B-Instruct-MLX
62
+
63
+ The Model [TheBlueObserver/Qwen2.5-Coder-0.5B-Instruct-MLX](https://huggingface.co/TheBlueObserver/Qwen2.5-Coder-0.5B-Instruct-MLX) was
64
+ converted to MLX format from [Qwen/Qwen2.5-Coder-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-0.5B-Instruct)
65
+ using mlx-lm version **0.20.2**.
66
+
67
+ ## Use with mlx
68
+
69
+ ```bash
70
+ pip install mlx-lm
71
+ ```
72
+
73
+ ```python
74
+ from mlx_lm import load, generate
75
+
76
+ model, tokenizer = load("TheBlueObserver/Qwen2.5-Coder-0.5B-Instruct-MLX")
77
+
78
+ prompt="hello"
79
+
80
+ if hasattr(tokenizer, "apply_chat_template") and tokenizer.chat_template is not None:
81
+ messages = [{"role": "user", "content": prompt}]
82
+ prompt = tokenizer.apply_chat_template(
83
+ messages, tokenize=False, add_generation_prompt=True
84
+ )
85
+
86
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
87
+ ```
88
+
89
+