Xin Liu commited on
Commit
9890ded
1 Parent(s): 607cef9

Signed-off-by: Xin Liu <sam@secondstate.io>

Files changed (1) hide show
  1. README.md +73 -6
README.md CHANGED
@@ -1,10 +1,77 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  # Baichuan2-13B-Chat-GGUF
2
 
3
- ## Prompt Template
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
 
5
- ```bash
6
- 以下内容为人类用户与与一位智能助手的对话。
7
 
8
- 用户:你好!
9
- 助手:
10
- ```
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: baichuan-inc/Baichuan2-13B-Chat
3
+ inference: false
4
+ library_name: transformers
5
+ license: other
6
+ model_creator: Baichuan Intelligent Technology
7
+ model_name: Baichuan2 13B Chat
8
+ model_type: baichuan
9
+ tasks:
10
+ - text-generation
11
+ quantized_by: Second State Inc.
12
+ language:
13
+ - en
14
+ - zh
15
+ ---
16
+
17
+ <!-- header start -->
18
+ <!-- 200823 -->
19
+ <div style="width: auto; margin-left: auto; margin-right: auto">
20
+ <img src="https://github.com/second-state/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
21
+ </div>
22
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
23
+ <!-- header end -->
24
+
25
  # Baichuan2-13B-Chat-GGUF
26
 
27
+ ## Original Model
28
+
29
+ [baichuan-inc/Baichuan2-13B-Chat](https://huggingface.co/baichuan-inc/Baichuan2-13B-Chat)
30
+
31
+ ## Run with LlamaEdge
32
+
33
+ - LlamaEdge version: [v0.2.4](https://github.com/second-state/LlamaEdge/releases/tag/0.2.4)
34
+
35
+ - Prompt template
36
+
37
+ - Prompt type: `baichuan-2`
38
+
39
+ - Prompt string
40
+
41
+ ```text
42
+ 以下内容为人类用户与与一位智能助手的对话。
43
+
44
+ 用户:你好!
45
+ 助手:
46
+ ```
47
+
48
+ - Reverse prompt: `用户:`
49
+
50
+ - Run as LlamaEdge service
51
+
52
+ ```bash
53
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Baichuan2-13B-Chat-Q5_K_M.gguf llama-api-server.wasm -p baichuan-2 -r '用户:'
54
+ ```
55
+
56
+ - Run as LlamaEdge command app
57
+
58
+ ```bash
59
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Baichuan2-13B-Chat-Q5_K_M.gguf llama-chat.wasm -p baichuan-2 -r '用户:'
60
+ ```
61
 
62
+ ## Quantized GGUF Models
 
63
 
64
+ | Name | Quant method | Bits | Size | Use case |
65
+ | ---- | ---- | ---- | ---- | ----- |
66
+ | [Baichuan2-13B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q2_K.gguf) | Q2_K | 2 | 6.5 GB| smallest, significant quality loss - not recommended for most purposes |
67
+ | [Baichuan2-13B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 7.67 GB| small, substantial quality loss |
68
+ | [Baichuan2-13B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 7.24 GB| very small, high quality loss |
69
+ | [Baichuan2-13B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 6.77 GB| very small, high quality loss |
70
+ | [Baichuan2-13B-Chat-Q4_0.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q4_0.gguf) | Q4_0 | 4 | 7.99 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
71
+ | [Baichuan2-13B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 9.00 GB| medium, balanced quality - recommended |
72
+ | [Baichuan2-13B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 8.37 GB| small, greater quality loss |
73
+ | [Baichuan2-13B-Chat-Q5_0.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q5_0.gguf) | Q5_0 | 5 | 9.64 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
74
+ | [Baichuan2-13B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 10.3 GB| large, very low quality loss - recommended |
75
+ | [Baichuan2-13B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 9.82 GB| large, low quality loss - recommended |
76
+ | [Baichuan2-13B-Chat-Q6_K.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q6_K.gguf) | Q6_K | 6 | 12.1 GB| very large, extremely low quality loss |
77
+ | [Baichuan2-13B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Baichuan2-13B-Chat-GGUF/blob/main/Baichuan2-13B-Chat-Q8_0.gguf) | Q8_0 | 8 | 14.8 GB| very large, extremely low quality loss - not recommended |