apepkuss79 commited on
Commit
98aa528
1 Parent(s): d520974

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +86 -0
README.md CHANGED
@@ -1,3 +1,89 @@
1
  ---
 
 
 
 
 
 
 
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: 01-ai/Yi-Coder-1.5B-Chat
3
+ inference: false
4
+ model_creator: 01-ai
5
+ model_name: Yi-Coder-1.5B-Chat
6
+ model_type: yi
7
+ pipeline_tag: text-generation
8
+ quantized_by: Second State Inc.
9
  license: apache-2.0
10
  ---
11
+
12
+ <!-- header start -->
13
+ <!-- 200823 -->
14
+ <div style="width: auto; margin-left: auto; margin-right: auto">
15
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
16
+ </div>
17
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
18
+ <!-- header end -->
19
+
20
+ # Yi-Coder-1.5B-Chat-GGUF
21
+
22
+ ## Original Model
23
+
24
+ [01-ai/Yi-Coder-1.5B-Chat](https://huggingface.co/01-ai/Yi-Coder-1.5B-Chat)
25
+
26
+ ## Run with LlamaEdge
27
+
28
+ <!-- - LlamaEdge version: [v0.10.0](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.10.0) and above -->
29
+
30
+ - LlamaEdge version: coming soon
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-Coder-1.5B-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-Coder-1.5B-Chat
59
+ ```
60
+
61
+ - Run as LlamaEdge command app
62
+
63
+ ```bash
64
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-Coder-1.5B-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-Coder-1.5B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q2_K.gguf) | Q2_K | 2 | 635 MB| smallest, significant quality loss - not recommended for most purposes |
76
+ | [Yi-Coder-1.5B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 826 MB| small, substantial quality loss |
77
+ | [Yi-Coder-1.5B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 768 MB| very small, high quality loss |
78
+ | [Yi-Coder-1.5B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 723 MB| very small, high quality loss |
79
+ | [Yi-Coder-1.5B-Chat-Q4_0.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_0.gguf) | Q4_0 | 4 | 866 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
80
+ | [Yi-Coder-1.5B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 964 MB| medium, balanced quality - recommended |
81
+ | [Yi-Coder-1.5B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 904 MB| small, greater quality loss |
82
+ | [Yi-Coder-1.5B-Chat-Q5_0.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q5_0.gguf) | Q5_0 | 5 | 1.03 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
83
+ | [Yi-Coder-1.5B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 1.10 GB| large, very low quality loss - recommended |
84
+ | [Yi-Coder-1.5B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 1.05 GB| large, low quality loss - recommended |
85
+ | [Yi-Coder-1.5B-Chat-Q6_K.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q6_K.gguf) | Q6_K | 6 | 1.28 GB| very large, extremely low quality loss |
86
+ | [Yi-Coder-1.5B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-Q8_0.gguf) | Q8_0 | 8 | 1.57 GB| very large, extremely low quality loss - not recommended |
87
+ | [Yi-Coder-1.5B-Chat-f16.gguf](https://huggingface.co/second-state/Yi-Coder-1.5B-Chat-GGUF/blob/main/Yi-Coder-1.5B-Chat-f16.gguf) | f16 | 16 | 2.95 GB| |
88
+
89
+ *Quantized with llama.cpp b3499*