Hugging Face's logo

second-state
/
Qwen2.5-14B-Instruct-GGUF

Text Generation
GGUF
English
qwen2
chat
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
608247a
·
verified ·
1 Parent(s): 060b7f7

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +86 -86
README.md CHANGED
@@ -1,86 +1,86 @@
1
- ---
2
- base_model: Qwen/Qwen2.5-14B-Instruct
3
- license: apache-2.0
4
- license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE
5
- model_creator: Qwen
6
- model_name: Qwen2.5-14B-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
- # Qwen2.5-14B-Instruct-GGUF
24
-
25
- ## Original Model
26
-
27
- [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-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: `128000`
48
-
49
- - Run as LlamaEdge service
50
-
51
- ```bash
52
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-14B-Instruct-Q5_K_M.gguf \
53
- llama-api-server.wasm \
54
- --model-name Qwen2.5-14B-Instruct \
55
- --prompt-template chatml \
56
- --ctx-size 128000
57
- ```
58
-
59
- - Run as LlamaEdge command app
60
-
61
- ```bash
62
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-14B-Instruct-Q5_K_M.gguf \
63
- llama-chat.wasm \
64
- --prompt-template chatml \
65
- --ctx-size 128000
66
- ```
67
-
68
- ## Quantized GGUF Models
69
-
70
- | Name | Quant method | Bits | Size | Use case |
71
- | ---- | ---- | ---- | ---- | ----- |
72
- | [Qwen2.5-14B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q2_K.gguf) | Q2_K | 2 | 3.02 GB| smallest, significant quality loss - not recommended for most purposes |
73
- | [Qwen2.5-14B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.09 GB| small, substantial quality loss |
74
- | [Qwen2.5-14B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 3.81 GB| very small, high quality loss |
75
- | [Qwen2.5-14B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.49 GB| very small, high quality loss |
76
- | [Qwen2.5-14B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.43 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
- | [Qwen2.5-14B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 4.68 GB| medium, balanced quality - recommended |
78
- | [Qwen2.5-14B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.46 GB| small, greater quality loss |
79
- | [Qwen2.5-14B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.32 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
- | [Qwen2.5-14B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.44 GB| large, very low quality loss - recommended |
81
- | [Qwen2.5-14B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.32 GB| large, low quality loss - recommended |
82
- | [Qwen2.5-14B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.25 GB| very large, extremely low quality loss |
83
- | [Qwen2.5-14B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 8.21 GB| very large, extremely low quality loss - not recommended |
84
- | [Qwen2.5-14B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-f16.gguf) | f16 | 16 | 15.2 GB| |
85
-
86
- *Quantized with llama.cpp b3751*
 
1
+ ---
2
+ base_model: Qwen/Qwen2.5-14B-Instruct
3
+ license: apache-2.0
4
+ license_link: https://huggingface.co/Qwen/Qwen2.5-14B-Instruct/blob/main/LICENSE
5
+ model_creator: Qwen
6
+ model_name: Qwen2.5-14B-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
+ # Qwen2.5-14B-Instruct-GGUF
24
+
25
+ ## Original Model
26
+
27
+ [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-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: `128000`
48
+
49
+ - Run as LlamaEdge service
50
+
51
+ ```bash
52
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-14B-Instruct-Q5_K_M.gguf \
53
+ llama-api-server.wasm \
54
+ --model-name Qwen2.5-14B-Instruct \
55
+ --prompt-template chatml \
56
+ --ctx-size 128000
57
+ ```
58
+
59
+ - Run as LlamaEdge command app
60
+
61
+ ```bash
62
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Qwen2.5-14B-Instruct-Q5_K_M.gguf \
63
+ llama-chat.wasm \
64
+ --prompt-template chatml \
65
+ --ctx-size 128000
66
+ ```
67
+
68
+ ## Quantized GGUF Models
69
+
70
+ | Name | Quant method | Bits | Size | Use case |
71
+ | ---- | ---- | ---- | ---- | ----- |
72
+ | [Qwen2.5-14B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q2_K.gguf) | Q2_K | 2 | 5.77 GB| smallest, significant quality loss - not recommended for most purposes |
73
+ | [Qwen2.5-14B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 7.92 GB| small, substantial quality loss |
74
+ | [Qwen2.5-14B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 7.34 GB| very small, high quality loss |
75
+ | [Qwen2.5-14B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 6.66 GB| very small, high quality loss |
76
+ | [Qwen2.5-14B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 8.52 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
77
+ | [Qwen2.5-14B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 8.99 GB| medium, balanced quality - recommended |
78
+ | [Qwen2.5-14B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 8.57 GB| small, greater quality loss |
79
+ | [Qwen2.5-14B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 10.3 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
80
+ | [Qwen2.5-14B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 10.5 GB| large, very low quality loss - recommended |
81
+ | [Qwen2.5-14B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 10.3 GB| large, low quality loss - recommended |
82
+ | [Qwen2.5-14B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q6_K.gguf) | Q6_K | 6 | 12.1 GB| very large, extremely low quality loss |
83
+ | [Qwen2.5-14B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 15.1 GB| very large, extremely low quality loss - not recommended |
84
+ | [Qwen2.5-14B-Instruct-f16.gguf](https://huggingface.co/second-state/Qwen2.5-14B-Instruct-GGUF/blob/main/Qwen2.5-14B-Instruct-f16.gguf) | f16 | 16 | 29.5 GB| |
85
+
86
+ *Quantized with llama.cpp b3751*