apepkuss79 commited on
Commit
161d605
1 Parent(s): 8736848

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +83 -0
README.md CHANGED
@@ -1,3 +1,86 @@
1
  ---
 
2
  license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: Qwen/Qwen2.5-0.5B-Instruct
3
  license: apache-2.0
4
+ license_link: https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/blob/main/LICENSE
5
+ model_creator: Qwen
6
+ model_name: Qwen2.5-0.5B-Instruct
7
+ quantized_by: Second State Inc.
8
+ language:
9
+ - en
10
+ pipeline_tag: text-generation
11
+ tags:
12
+ - chat
13
  ---
14
+
15
+ <!-- header start -->
16
+ <!-- 200823 -->
17
+ <div style="width: auto; margin-left: auto; margin-right: auto">
18
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
19
+ </div>
20
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
21
+ <!-- header end -->
22
+
23
+ # Qwen2.5-0.5B-Instruct-GGUF
24
+
25
+ ## Original Model
26
+
27
+ [Qwen/Qwen2.5-0.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct)
28
+
29
+ ## Run with LlamaEdge
30
+
31
+ - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3)
32
+
33
+ - Prompt template
34
+
35
+ - Prompt type: `chatml`
36
+
37
+ - Prompt string
38
+
39
+ ```text
40
+ <|im_start|>system
41
+ {system_message}<|im_end|>
42
+ <|im_start|>user
43
+ {prompt}<|im_end|>
44
+ <|im_start|>assistant
45
+ ```
46
+
47
+ - Context size: `32000`
48
+
49
+ - Run as LlamaEdge service
50
+
51
+ ```bash
52
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-0.5B-Instruct-Q5_K_M.gguf \
53
+ llama-api-server.wasm \
54
+ --model-name Qwen2.5-0.5B-Instruct \
55
+ --prompt-template chatml \
56
+ --ctx-size 32000
57
+ ```
58
+
59
+ - Run as LlamaEdge command app
60
+
61
+ ```bash
62
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-0.5B-Instruct-Q5_K_M.gguf \
63
+ llama-chat.wasm \
64
+ --prompt-template chatml \
65
+ --ctx-size 32000
66
+ ```
67
+
68
+ ## Quantized GGUF Models
69
+
70
+ | Name | Quant method | Bits | Size | Use case |
71
+ | ---- | ---- | ---- | ---- | ----- |
72
+ | [Qwen2.5-0.5B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q2_K.gguf) | Q2_K | 2 | 339 MB| smallest, significant quality loss - not recommended for most purposes |
73
+ | [Qwen2.5-0.5B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 369 MB| small, substantial quality loss |
74
+ | [Qwen2.5-0.5B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 355 MB| very small, high quality loss |
75
+ | [Qwen2.5-0.5B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 338 MB| very small, high quality loss |
76
+ | [Qwen2.5-0.5B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 352 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
+ | [Qwen2.5-0.5B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 398 MB| medium, balanced quality - recommended |
78
+ | [Qwen2.5-0.5B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 385 MB| small, greater quality loss |
79
+ | [Qwen2.5-0.5B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 397 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
+ | [Qwen2.5-0.5B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 420 MB| large, very low quality loss - recommended |
81
+ | [Qwen2.5-0.5B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 413 MB| large, low quality loss - recommended |
82
+ | [Qwen2.5-0.5B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q6_K.gguf) | Q6_K | 6 | 506 MB| very large, extremely low quality loss |
83
+ | [Qwen2.5-0.5B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 531 MB| very large, extremely low quality loss - not recommended |
84
+ | [Qwen2.5-0.5B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-0.5B-Instruct-GGUF/blob/main/Qwen2.5-0.5B-Instruct-f16.gguf) | f16 | 16 | 994 MB| |
85
+
86
+ *Quantized with llama.cpp b3751*