Hugging Face's logo

second-state
/
DeepSeek-V2-Lite-Chat-GGUF

Text Generation
Transformers
GGUF
deepseek_v2
custom_code
conversational
Model card Files Community
1
apepkuss79 commited on
Commit
fbba16c
•
1 Parent(s): 93cbae0

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +87 -87
README.md CHANGED
@@ -1,88 +1,88 @@
1
- ---
2
- base_model: deepseek-ai/DeepSeek-V2-Lite-Chat
3
- inference: false
4
- license: other
5
- license_name: deepseek
6
- license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
7
- model_creator: DeepSeek-ai
8
- model_name: DeepSeek-V2-Lite-Chat
9
- model_type: deepseek
10
- quantized_by: Second State Inc.
11
- ---
12
-
13
- <!-- header start -->
14
- <!-- 200823 -->
15
- <div style="width: auto; margin-left: auto; margin-right: auto">
16
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
- </div>
18
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
19
- <!-- header end -->
20
-
21
- # DeepSeek-V2-Lite-Chat-GGUF
22
-
23
- ## Original Model
24
-
25
- [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat)
26
-
27
- ## Run with LlamaEdge
28
-
29
- - LlamaEdge version: coming soon
30
-
31
- - Prompt template
32
-
33
- - Prompt type: `deepseek-chat-2`
34
-
35
- - Prompt string
36
-
37
- ```text
38
- <|begin_of_sentence|>{system_message}
39
-
40
- User: {user_message_1}
41
-
42
- Assistant: {assistant_message_1}<|end_of_sentence|>User: {user_message_2}
43
-
44
- Assistant:
45
- ```
46
-
47
- - Context size: `128000`
48
-
49
- <!-- - Run as LlamaEdge service
50
-
51
- ```bash
52
- wasmedge --dir .:. \
53
- --nn-preload default:GGML:AUTO:DeepSeek-V2-Lite-Chat-Q5_K_M.gguf \
54
- llama-api-server.wasm \
55
- --prompt-template deepseek-chat-2 \
56
- --ctx-size 128000 \
57
- --model-name DeepSeek-V2-Lite-Chat
58
- ```
59
-
60
- - Run as LlamaEdge command app
61
-
62
- ```bash
63
- wasmedge --dir .:. \
64
- --nn-preload default:GGML:AUTO:DeepSeek-V2-Lite-Chat-Q5_K_M.gguf \
65
- llama-chat.wasm \
66
- --prompt-template deepseek-chat-2 \
67
- --ctx-size 128000
68
- ``` -->
69
-
70
- ## Quantized GGUF Models
71
-
72
- | Name | Quant method | Bits | Size | Use case |
73
- | ---- | ---- | ---- | ---- | ----- |
74
- | [DeepSeek-V2-Lite-Chat-Q2_K.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q2_K.gguf) | Q2_K | 2 | 6.43 GB| smallest, significant quality loss - not recommended for most purposes |
75
- | [DeepSeek-V2-Lite-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 8.46 GB| small, substantial quality loss |
76
- | [DeepSeek-V2-Lite-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 8.13 GB| very small, high quality loss |
77
- | [DeepSeek-V2-Lite-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 7.49 GB| very small, high quality loss |
78
- | [DeepSeek-V2-Lite-Chat-Q4_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_0.gguf) | Q4_0 | 4 | 8.91 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
79
- | [DeepSeek-V2-Lite-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 10.4 GB| medium, balanced quality - recommended |
80
- | [DeepSeek-V2-Lite-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 9.53 GB| small, greater quality loss |
81
- | [DeepSeek-V2-Lite-Chat-Q5_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_0.gguf) | Q5_0 | 5 | 10.8 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
82
- | [DeepSeek-V2-Lite-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 11.9 GB| large, very low quality loss - recommended |
83
- | [DeepSeek-V2-Lite-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 11.1 GB| large, low quality loss - recommended |
84
- | [DeepSeek-V2-Lite-Chat-Q6_K.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q6_K.gguf) | Q6_K | 6 | 14.1 GB| very large, extremely low quality loss |
85
- | [DeepSeek-V2-Lite-Chat-Q8_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q8_0.gguf) | Q8_0 | 8 | 16.7 GB| very large, extremely low quality loss - not recommended |
86
- | [DeepSeek-V2-Lite-Chat-f16.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-f16.gguf) | f16 | 16 | 31.4 GB| |
87
-
88
  *Quatized with llama.cpp b3333*
 
1
+ ---
2
+ base_model: deepseek-ai/DeepSeek-V2-Lite-Chat
3
+ inference: false
4
+ license: other
5
+ license_name: deepseek
6
+ license_link: https://github.com/deepseek-ai/DeepSeek-V2/blob/main/LICENSE-MODEL
7
+ model_creator: DeepSeek-ai
8
+ model_name: DeepSeek-V2-Lite-Chat
9
+ model_type: deepseek
10
+ quantized_by: Second State Inc.
11
+ ---
12
+
13
+ <!-- header start -->
14
+ <!-- 200823 -->
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
19
+ <!-- header end -->
20
+
21
+ # DeepSeek-V2-Lite-Chat-GGUF
22
+
23
+ ## Original Model
24
+
25
+ [deepseek-ai/DeepSeek-V2-Lite-Chat](https://huggingface.co/deepseek-ai/DeepSeek-V2-Lite-Chat)
26
+
27
+ ## Run with LlamaEdge
28
+
29
+ - LlamaEdge version: [v0.12.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.3) and above
30
+
31
+ - Prompt template
32
+
33
+ - Prompt type: `deepseek-chat-2`
34
+
35
+ - Prompt string
36
+
37
+ ```text
38
+ <|begin_of_sentence|>{system_message}
39
+
40
+ User: {user_message_1}
41
+
42
+ Assistant: {assistant_message_1}<|end_of_sentence|>User: {user_message_2}
43
+
44
+ Assistant:
45
+ ```
46
+
47
+ - Context size: `128000`
48
+
49
+ <!-- - Run as LlamaEdge service
50
+
51
+ ```bash
52
+ wasmedge --dir .:. \
53
+ --nn-preload default:GGML:AUTO:DeepSeek-V2-Lite-Chat-Q5_K_M.gguf \
54
+ llama-api-server.wasm \
55
+ --prompt-template deepseek-chat-2 \
56
+ --ctx-size 128000 \
57
+ --model-name DeepSeek-V2-Lite-Chat
58
+ ```
59
+
60
+ - Run as LlamaEdge command app
61
+
62
+ ```bash
63
+ wasmedge --dir .:. \
64
+ --nn-preload default:GGML:AUTO:DeepSeek-V2-Lite-Chat-Q5_K_M.gguf \
65
+ llama-chat.wasm \
66
+ --prompt-template deepseek-chat-2 \
67
+ --ctx-size 128000
68
+ ``` -->
69
+
70
+ ## Quantized GGUF Models
71
+
72
+ | Name | Quant method | Bits | Size | Use case |
73
+ | ---- | ---- | ---- | ---- | ----- |
74
+ | [DeepSeek-V2-Lite-Chat-Q2_K.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q2_K.gguf) | Q2_K | 2 | 6.43 GB| smallest, significant quality loss - not recommended for most purposes |
75
+ | [DeepSeek-V2-Lite-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 8.46 GB| small, substantial quality loss |
76
+ | [DeepSeek-V2-Lite-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 8.13 GB| very small, high quality loss |
77
+ | [DeepSeek-V2-Lite-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 7.49 GB| very small, high quality loss |
78
+ | [DeepSeek-V2-Lite-Chat-Q4_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_0.gguf) | Q4_0 | 4 | 8.91 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
79
+ | [DeepSeek-V2-Lite-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 10.4 GB| medium, balanced quality - recommended |
80
+ | [DeepSeek-V2-Lite-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 9.53 GB| small, greater quality loss |
81
+ | [DeepSeek-V2-Lite-Chat-Q5_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_0.gguf) | Q5_0 | 5 | 10.8 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
82
+ | [DeepSeek-V2-Lite-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 11.9 GB| large, very low quality loss - recommended |
83
+ | [DeepSeek-V2-Lite-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 11.1 GB| large, low quality loss - recommended |
84
+ | [DeepSeek-V2-Lite-Chat-Q6_K.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q6_K.gguf) | Q6_K | 6 | 14.1 GB| very large, extremely low quality loss |
85
+ | [DeepSeek-V2-Lite-Chat-Q8_0.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-Q8_0.gguf) | Q8_0 | 8 | 16.7 GB| very large, extremely low quality loss - not recommended |
86
+ | [DeepSeek-V2-Lite-Chat-f16.gguf](https://huggingface.co/second-state/DeepSeek-V2-Lite-Chat-GGUF/blob/main/DeepSeek-V2-Lite-Chat-f16.gguf) | f16 | 16 | 31.4 GB| |
87
+
88
  *Quatized with llama.cpp b3333*