apepkuss79 commited on
Commit
bd6727e
1 Parent(s): b017f2d

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +87 -1
README.md CHANGED
@@ -1,3 +1,89 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: 01-ai/Yi-1.5-9B-Chat
3
+ inference: false
4
+ license: other
5
+ license_link: LICENSE
6
+ license_name: yi-license
7
+ model_creator: 01-ai
8
+ model_name: Yi-1.5-9B-Chat
9
+ model_type: yi
10
+ pipeline_tag: text-generation
11
+ quantized_by: Second State Inc.
12
  ---
13
+
14
+ <!-- header start -->
15
+ <!-- 200823 -->
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
20
+ <!-- header end -->
21
+
22
+ # Yi-1.5-9B-Chat-GGUF
23
+
24
+ ## Original Model
25
+
26
+ [01-ai/Yi-1.5-9B-Chat](https://huggingface.co/01-ai/Yi-1.5-9B-Chat)
27
+
28
+ ## Run with LlamaEdge
29
+
30
+ - LlamaEdge version: [v0.10.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.10.0) and above
31
+
32
+ - Prompt template
33
+
34
+ - Prompt type: `chatml`
35
+
36
+ - Prompt string
37
+
38
+ ```text
39
+ <|im_start|>system
40
+ {system_message}<|im_end|>
41
+ <|im_start|>user
42
+ {prompt}<|im_end|>
43
+ <|im_start|>assistant
44
+ ```
45
+
46
+ - Reverse prompt: `<|im_end|>`
47
+
48
+ - Context size: `4096`
49
+
50
+ - Run as LlamaEdge service
51
+
52
+ ```bash
53
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-Q5_K_M.gguf \
54
+ llama-api-server.wasm \
55
+ --prompt-template chatml \
56
+ --reverse-prompt '<|im_end|>' \
57
+ --ctx-size 4096 \
58
+ --model-name Yi-1.5-9B-Chat
59
+ ```
60
+
61
+ - Run as LlamaEdge command app
62
+
63
+ ```bash
64
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-1.5-9B-Chat-Q5_K_M.gguf \
65
+ llama-chat.wasm \
66
+ --prompt-template chatml \
67
+ --reverse-prompt '<|im_end|>' \
68
+ --ctx-size 4096
69
+ ```
70
+
71
+ ## Quantized GGUF Models
72
+
73
+ | Name | Quant method | Bits | Size | Use case |
74
+ | ---- | ---- | ---- | ---- | ----- |
75
+ | [Yi-1.5-9B-Chat-Q2_K.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q2_K.gguf) | Q2_K | 2 |3.35 GB| smallest, significant quality loss - not recommended for most purposes |
76
+ | [Yi-1.5-9B-Chat-Q3_K_L.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 3.24 GB| small, substantial quality loss |
77
+ | [Yi-1.5-9B-Chat-Q3_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 2.99 GB| very small, high quality loss |
78
+ | [Yi-1.5-9B-Chat-Q3_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 2.71 GB| very small, high quality loss |
79
+ | [Yi-1.5-9B-Chat-Q4_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q4_0.gguf) | Q4_0 | 4 | 3.48 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
80
+ | [Yi-1.5-9B-Chat-Q4_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 3.67 GB| medium, balanced quality - recommended |
81
+ | [Yi-1.5-9B-Chat-Q4_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 3.50 GB| small, greater quality loss |
82
+ | [Yi-1.5-9B-Chat-Q5_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q5_0.gguf) | Q5_0 | 5 | 4.20 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
83
+ | [Yi-1.5-9B-Chat-Q5_K_M.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 4.30 GB| large, very low quality loss - recommended |
84
+ | [Yi-1.5-9B-Chat-Q5_K_S.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 4.20 GB| large, low quality loss - recommended |
85
+ | [Yi-1.5-9B-Chat-Q6_K.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q6_K.gguf) | Q6_K | 6 | 4.97 GB| very large, extremely low quality loss |
86
+ | [Yi-1.5-9B-Chat-Q8_0.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-Q8_0.gguf) | Q8_0 | 8 | 6.44 GB| very large, extremely low quality loss - not recommended |
87
+ | [Yi-1.5-9B-Chat-f16.gguf](https://huggingface.co/gaianet/Yi-1.5-9B-Chat-GGUF/blob/main/Yi-1.5-9B-Chat-f16.gguf) | f16 | 16 | 17.7 GB| |
88
+
89
+ *Quantized with llama.cpp b2824*