Hugging Face's logo

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

GGUF
llama
conversational
Model card Files Community
apepkuss79 commited on
Commit
4b301f8
·
verified ·
1 Parent(s): 495bd4e

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +69 -71
README.md CHANGED
@@ -1,72 +1,70 @@
1
- ---
2
- base_model: ByteDance-Seed/Seed-Coder-8B-Reasoning
3
- license: mit
4
- model_creator: ByteDance-Seed
5
- model_name: Seed-Coder-8B-Reasoning
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-Reasoning-GGUF
18
-
19
- ## Original Model
20
-
21
- [ByteDance-Seed/Seed-Coder-8B-Reasoning](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Reasoning)
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-reasoning`
32
-
33
- - Prompt string
34
-
35
- ```text
36
- <[begin▁of▁sentence]>user
37
- {user_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
38
- {assistant_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>user
39
- {user_message_2}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
40
- ```
41
-
42
- - Context size: `32000`
43
-
44
- - Run as LlamaEdge service
45
-
46
- ```bash
47
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:Seed-Coder-8B-Reasoning-Q5_K_M.gguf \
48
- llama-api-server.wasm \
49
- --model-name Seed-Coder-8B-Reasoning \
50
- --prompt-template seed-reasoning \
51
- --ctx-size 32000
52
- ```
53
-
54
- ## Quantized GGUF Models
55
-
56
- | Name | Quant method | Bits | Size | Use case |
57
- | ---- | ---- | ---- | ---- | ----- |
58
- | [Seed-Coder-8B-Reasoning-Q2_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q2_K.gguf) | Q2_K | 2 | 3.30 GB| smallest, significant quality loss - not recommended for most purposes |
59
- | [Seed-Coder-8B-Reasoning-Q3_K_L.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q3_K_L.gguf) | Q3_K_L | 3 | 4.46 GB| small, substantial quality loss |
60
- | [Seed-Coder-8B-Reasoning-Q3_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q3_K_M.gguf) | Q3_K_M | 3 | 4.15 GB| very small, high quality loss |
61
- | [Seed-Coder-8B-Reasoning-Q3_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q3_K_S.gguf) | Q3_K_S | 3 | 3.80 GB| very small, high quality loss |
62
- | [Seed-Coder-8B-Reasoning-Q4_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q4_0.gguf) | Q4_0 | 4 | 4.81 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
63
- | [Seed-Coder-8B-Reasoning-Q4_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q4_K_M.gguf) | Q4_K_M | 4 | 5.07 GB| medium, balanced quality - recommended |
64
- | [Seed-Coder-8B-Reasoning-Q4_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q4_K_S.gguf) | Q4_K_S | 4 | 4.84 GB| small, greater quality loss |
65
- | [Seed-Coder-8B-Reasoning-Q5_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q5_0.gguf) | Q5_0 | 5 | 5.76 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
66
- | [Seed-Coder-8B-Reasoning-Q5_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q5_K_M.gguf) | Q5_K_M | 5 | 5.90 GB| large, very low quality loss - recommended |
67
- | [Seed-Coder-8B-Reasoning-Q5_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q5_K_S.gguf) | Q5_K_S | 5 | 5.76 GB| large, low quality loss - recommended |
68
- | [Seed-Coder-8B-Reasoning-Q6_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q6_K.gguf) | Q6_K | 6 | 6.78 GB| very large, extremely low quality loss |
69
- | [Seed-Coder-8B-Reasoning-Q8_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q8_0.gguf) | Q8_0 | 8 | 8.77 GB| very large, extremely low quality loss - not recommended |
70
- | [Seed-Coder-8B-Reasoning-f16.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-f16.gguf) | f16 | 16 | 16.6 GB| |
71
-
72
  *Quantized with llama.cpp b5341*
 
1
+ ---
2
+ base_model: ByteDance-Seed/Seed-Coder-8B-Reasoning
3
+ license: mit
4
+ model_creator: ByteDance-Seed
5
+ model_name: Seed-Coder-8B-Reasoning
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-Reasoning-GGUF
18
+
19
+ ## Original Model
20
+
21
+ [ByteDance-Seed/Seed-Coder-8B-Reasoning](https://huggingface.co/ByteDance-Seed/Seed-Coder-8B-Reasoning)
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-reasoning`
30
+
31
+ - Prompt string
32
+
33
+ ```text
34
+ <[begin▁of▁sentence]>user
35
+ {user_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
36
+ {assistant_message_1}<[end▁of▁sentence]><[begin▁of▁sentence]>user
37
+ {user_message_2}<[end▁of▁sentence]><[begin▁of▁sentence]>assistant
38
+ ```
39
+
40
+ - Context size: `32000`
41
+
42
+ - Run as LlamaEdge service
43
+
44
+ ```bash
45
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Seed-Coder-8B-Reasoning-Q5_K_M.gguf \
46
+ llama-api-server.wasm \
47
+ --model-name Seed-Coder-8B-Reasoning \
48
+ --prompt-template seed-reasoning \
49
+ --ctx-size 32000
50
+ ```
51
+
52
+ ## Quantized GGUF Models
53
+
54
+ | Name | Quant method | Bits | Size | Use case |
55
+ | ---- | ---- | ---- | ---- | ----- |
56
+ | [Seed-Coder-8B-Reasoning-Q2_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q2_K.gguf) | Q2_K | 2 | 3.30 GB| smallest, significant quality loss - not recommended for most purposes |
57
+ | [Seed-Coder-8B-Reasoning-Q3_K_L.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q3_K_L.gguf) | Q3_K_L | 3 | 4.46 GB| small, substantial quality loss |
58
+ | [Seed-Coder-8B-Reasoning-Q3_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q3_K_M.gguf) | Q3_K_M | 3 | 4.15 GB| very small, high quality loss |
59
+ | [Seed-Coder-8B-Reasoning-Q3_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q3_K_S.gguf) | Q3_K_S | 3 | 3.80 GB| very small, high quality loss |
60
+ | [Seed-Coder-8B-Reasoning-Q4_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q4_0.gguf) | Q4_0 | 4 | 4.81 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
61
+ | [Seed-Coder-8B-Reasoning-Q4_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q4_K_M.gguf) | Q4_K_M | 4 | 5.07 GB| medium, balanced quality - recommended |
62
+ | [Seed-Coder-8B-Reasoning-Q4_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q4_K_S.gguf) | Q4_K_S | 4 | 4.84 GB| small, greater quality loss |
63
+ | [Seed-Coder-8B-Reasoning-Q5_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q5_0.gguf) | Q5_0 | 5 | 5.76 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
64
+ | [Seed-Coder-8B-Reasoning-Q5_K_M.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q5_K_M.gguf) | Q5_K_M | 5 | 5.90 GB| large, very low quality loss - recommended |
65
+ | [Seed-Coder-8B-Reasoning-Q5_K_S.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q5_K_S.gguf) | Q5_K_S | 5 | 5.76 GB| large, low quality loss - recommended |
66
+ | [Seed-Coder-8B-Reasoning-Q6_K.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q6_K.gguf) | Q6_K | 6 | 6.78 GB| very large, extremely low quality loss |
67
+ | [Seed-Coder-8B-Reasoning-Q8_0.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-Q8_0.gguf) | Q8_0 | 8 | 8.77 GB| very large, extremely low quality loss - not recommended |
68
+ | [Seed-Coder-8B-Reasoning-f16.gguf](https://huggingface.co/second-state/Seed-Coder-8B-Reasoning-GGUF/blob/main/Seed-Coder-8B-Reasoning-f16.gguf) | f16 | 16 | 16.6 GB| |
69
+
 
 
70
  *Quantized with llama.cpp b5341*