Hugging Face's logo

second-state
/
Seed-Coder-8B-Instruct-GGUF

GGUF
llama
conversational
Model card Files Community
1
apepkuss79 commited on
Commit
4642c3a
·
verified ·
1 Parent(s): d7fc517

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +72 -74
README.md CHANGED
@@ -1,75 +1,73 @@
1
- ---
2
- base_model: ByteDance-Seed/Seed-Coder-8B-Instruct
3
- license: mit
4
- model_creator: ByteDance-Seed
5
- model_name: Seed-Coder-8B-Instruct
6
- quantized_by: Second State Inc.
7
- ---
8
-
9
- <!-- header start -->
10
- <!-- 200823 -->
11
- <div style="width: auto; margin-left: auto; margin-right: auto">
12
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
13
- </div>
14
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
15
- <!-- header end -->
16
-
17
- # Seed-Coder-8B-Instruct-GGUF
18
-
19
- ## Original Model
20
-
21
- [ByteDance-Seed/Seed-Coder-8B-Instruct](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct)
22
-
23
- ## Run with LlamaEdge
24
-
25
- - LlamaEdge version: coming soon
26
-
27
- <!-- - LlamaEdge version: [v0.17.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.17.0) and above -->
28
-
29
- - Prompt template
30
-
31
- - Prompt type: `seed-instruct`
32
-
33
- - Prompt string
34
-
35
- ```text
36
- <[begin▁of▁sentence]>system
37
- {system_message}
38
-
39
- <[end▁of▁sentence]><[begin▁of▁sentence]>user
40
- {user_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
41
- {assistant_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>user
42
- {user_message_2}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
43
- ```
44
-
45
- - Context size: `32000`
46
-
47
- - Run as LlamaEdge service
48
-
49
- ```bash
50
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Seed-Coder-8B-Instruct-Q5_K_M.gguf \
51
- llama-api-server.wasm \
52
- --model-name Seed-Coder-8B-Instruct \
53
- --prompt-template seed-instruct \
54
- --ctx-size 32000
55
- ```
56
-
57
- ## Quantized GGUF Models
58
-
59
- | Name | Quant method | Bits | Size | Use case |
60
- | ---- | ---- | ---- | ---- | ----- |
61
- | [Seed-Coder-8B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q2_K.gguf) | Q2_K | 2 | 3.30 GB| smallest, significant quality loss - not recommended for most purposes |
62
- | [Seed-Coder-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.46 GB| small, substantial quality loss |
63
- | [Seed-Coder-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 4.15 GB| very small, high quality loss |
64
- | [Seed-Coder-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.80 GB| very small, high quality loss |
65
- | [Seed-Coder-8B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.81 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
66
- | [Seed-Coder-8B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 5.07 GB| medium, balanced quality - recommended |
67
- | [Seed-Coder-8B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.84 GB| small, greater quality loss |
68
- | [Seed-Coder-8B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.76 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
69
- | [Seed-Coder-8B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.90 GB| large, very low quality loss - recommended |
70
- | [Seed-Coder-8B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.76 GB| large, low quality loss - recommended |
71
- | [Seed-Coder-8B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.78 GB| very large, extremely low quality loss |
72
- | [Seed-Coder-8B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 8.77 GB| very large, extremely low quality loss - not recommended |
73
- | [Seed-Coder-8B-Instruct-f16.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-f16.gguf) | f16 | 16 | 16.6 GB| |
74
-
75
  *Quantized with llama.cpp b5341*
 
1
+ ---
2
+ base_model: ByteDance-Seed/Seed-Coder-8B-Instruct
3
+ license: mit
4
+ model_creator: ByteDance-Seed
5
+ model_name: Seed-Coder-8B-Instruct
6
+ quantized_by: Second State Inc.
7
+ ---
8
+
9
+ <!-- header start -->
10
+ <!-- 200823 -->
11
+ <div style="width: auto; margin-left: auto; margin-right: auto">
12
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
13
+ </div>
14
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
15
+ <!-- header end -->
16
+
17
+ # Seed-Coder-8B-Instruct-GGUF
18
+
19
+ ## Original Model
20
+
21
+ [ByteDance-Seed/Seed-Coder-8B-Instruct](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Instruct)
22
+
23
+ ## Run with LlamaEdge
24
+
25
+ - LlamaEdge version: [v0.18.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.18.4) and above
26
+
27
+ - Prompt template
28
+
29
+ - Prompt type: `seed-instruct`
30
+
31
+ - Prompt string
32
+
33
+ ```text
34
+ <[begin▁of▁sentence]>system
35
+ {system_message}
36
+
37
+ <[end▁of▁sentence]><[begin▁of▁sentence]>user
38
+ {user_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
39
+ {assistant_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>user
40
+ {user_message_2}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
41
+ ```
42
+
43
+ - Context size: `32000`
44
+
45
+ - Run as LlamaEdge service
46
+
47
+ ```bash
48
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Seed-Coder-8B-Instruct-Q5_K_M.gguf \
49
+ llama-api-server.wasm \
50
+ --model-name Seed-Coder-8B-Instruct \
51
+ --prompt-template seed-instruct \
52
+ --ctx-size 32000
53
+ ```
54
+
55
+ ## Quantized GGUF Models
56
+
57
+ | Name | Quant method | Bits | Size | Use case |
58
+ | ---- | ---- | ---- | ---- | ----- |
59
+ | [Seed-Coder-8B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q2_K.gguf) | Q2_K | 2 | 3.30 GB| smallest, significant quality loss - not recommended for most purposes |
60
+ | [Seed-Coder-8B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 4.46 GB| small, substantial quality loss |
61
+ | [Seed-Coder-8B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 4.15 GB| very small, high quality loss |
62
+ | [Seed-Coder-8B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 3.80 GB| very small, high quality loss |
63
+ | [Seed-Coder-8B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 4.81 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
64
+ | [Seed-Coder-8B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 5.07 GB| medium, balanced quality - recommended |
65
+ | [Seed-Coder-8B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 4.84 GB| small, greater quality loss |
66
+ | [Seed-Coder-8B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 5.76 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
67
+ | [Seed-Coder-8B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 5.90 GB| large, very low quality loss - recommended |
68
+ | [Seed-Coder-8B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 5.76 GB| large, low quality loss - recommended |
69
+ | [Seed-Coder-8B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q6_K.gguf) | Q6_K | 6 | 6.78 GB| very large, extremely low quality loss |
70
+ | [Seed-Coder-8B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 8.77 GB| very large, extremely low quality loss - not recommended |
71
+ | [Seed-Coder-8B-Instruct-f16.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Instruct-GGUF/blob/main/Seed-Coder-8B-Instruct-f16.gguf) | f16 | 16 | 16.6 GB| |
72
+
 
 
73
  *Quantized with llama.cpp b5341*