Hugging Face's logo

second-state
/
Llama3-8B-Chinese-Chat-GGUF

Text Generation
GGUF
English
Chinese
llama-factory
orpo
conversational
Model card Files Community
Xin Liu commited on
Commit
40ee6b7
•
1 Parent(s): 3b65d18

Update

Browse files

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

Files changed (1) hide show
  1. README.md +91 -1
README.md CHANGED
@@ -1,3 +1,93 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: other
3
+ license_name: llama3
4
+ base_model: shenzhi-wang/Llama3-8B-Chinese-Chat
5
+ inference: false
6
+ model_creator: shenzhi-wang
7
+ model_type: llama
8
+ pipeline_tag: text-generation
9
+ quantized_by: Second State Inc.
10
+ language:
11
+ - en
12
+ - zh
13
+ tags:
14
+ - llama-factory
15
+ - orpo
16
  ---
17
+
18
+ <!-- header start -->
19
+ <!-- 200823 -->
20
+ <div style="width: auto; margin-left: auto; margin-right: auto">
21
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
22
+ </div>
23
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
24
+ <!-- header end -->
25
+
26
+ # Llama3-8B-Chinese-Chat-GGUF
27
+
28
+ ## Original Model
29
+
30
+ [shenzhi-wang/Llama3-8B-Chinese-Chat](https://huggingface.co/shenzhi-wang/Llama3-8B-Chinese-Chat)
31
+
32
+ ## Run with LlamaEdge
33
+
34
+ - LlamaEdge version: [v0.8.6](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.6) and above
35
+
36
+ - Prompt template
37
+
38
+ - Prompt type: `llama-3-chat`
39
+
40
+ - Prompt string
41
+
42
+ ```text
43
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
44
+
45
+ {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
46
+
47
+ {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
48
+
49
+ {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
50
+
51
+ {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
52
+ ```
53
+
54
+ - Context size: `4096`
55
+
56
+ - Run as LlamaEdge service
57
+
58
+ ```bash
59
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama3-8B-Chinese-Chat-Q5_K_M.gguf \
60
+ llama-api-server.wasm \
61
+ --prompt-template llama-3-chat \
62
+ --ctx-size 4096 \
63
+ --model-name Llama-3-8b-Chinese-Chat \
64
+ ```
65
+
66
+ - Run as LlamaEdge command app
67
+
68
+ ```bash
69
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama3-8B-Chinese-Chat-Q5_K_M.gguf \
70
+ llama-chat.wasm \
71
+ --prompt-template Llama-3-8b-Chinese-Chat \
72
+ --ctx-size 4096 \
73
+ ```
74
+
75
+ ## Quantized GGUF Models
76
+
77
+ | Name | Quant method | Bits | Size | Use case |
78
+ | ---- | ---- | ---- | ---- | ----- |
79
+ | [Llama3-8B-Chinese-Chat-Q2_K.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q2_K.gguf) | Q2_K | 2 | 3.18 GB| smallest, significant quality loss - not recommended for most purposes |
80
+ | [Llama3-8B-Chinese-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 4.32 GB| small, substantial quality loss |
81
+ | [Llama3-8B-Chinese-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 4.02 GB| very small, high quality loss |
82
+ | [Llama3-8B-Chinese-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 3.66 GB| very small, high quality loss |
83
+ | [Llama3-8B-Chinese-Chat-Q4_0.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q4_0.gguf) | Q4_0 | 4 | 4.66 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
84
+ | [Llama3-8B-Chinese-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 4.92 GB| medium, balanced quality - recommended |
85
+ | [Llama3-8B-Chinese-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 4.69 GB| small, greater quality loss |
86
+ | [Llama3-8B-Chinese-Chat-Q5_0.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q5_0.gguf) | Q5_0 | 5 | 5.6 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
87
+ | [Llama3-8B-Chinese-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 5.73 GB| large, very low quality loss - recommended |
88
+ | [Llama3-8B-Chinese-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 5.6 GB| large, low quality loss - recommended |
89
+ | [Llama3-8B-Chinese-Chat-Q6_K.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q6_K.gguf) | Q6_K | 6 | 6.6 GB| very large, extremely low quality loss |
90
+ | [Llama3-8B-Chinese-Chat-Q8_0.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-Q8_0.gguf) | Q8_0 | 8 | 8.54 GB| very large, extremely low quality loss - not recommended |
91
+ | [Llama3-8B-Chinese-Chat-f16.gguf](https://huggingface.co/second-state/Llama3-8B-Chinese-Chat-GGUF/blob/main/Llama3-8B-Chinese-Chat-f16.gguf) | f16 | 16 | 16.1 GB| |
92
+
93
+ *Quantized with llama.cpp b2734.*