apepkuss79 commited on
Commit
7b39624
1 Parent(s): b847600

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +106 -1
README.md CHANGED
@@ -1,3 +1,108 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: llama3.1
3
+ model_name: Meta-Llama-3.1-70B-Instruct
4
+ base_model: meta-llama/Meta-Llama-3.1-70B-Instruct
5
+ inference: false
6
+ model_creator: Meta Llama3
7
+ model_type: llama
8
+ pipeline_tag: text-generation
9
+ quantized_by: Second State Inc.
10
+ language:
11
+ - en
12
+ - de
13
+ - fr
14
+ - it
15
+ - pt
16
+ - hi
17
+ - es
18
+ - th
19
+ tags:
20
+ - facebook
21
+ - meta
22
+ - pytorch
23
+ - llama
24
+ - llama-3
25
  ---
26
+
27
+ <!-- header start -->
28
+ <!-- 200823 -->
29
+ <div style="width: auto; margin-left: auto; margin-right: auto">
30
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
31
+ </div>
32
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
33
+ <!-- header end -->
34
+
35
+ # Meta-Llama-3.1-70B-Instruct-GGUF
36
+
37
+ ## Original Model
38
+
39
+ [meta-llama/Meta-Llama-3.1-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-70B-Instruct)
40
+
41
+ ## Run with LlamaEdge
42
+
43
+ - LlamaEdge version: [v0.8.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.8.3) and above
44
+
45
+ - Prompt template
46
+
47
+ - Prompt type: `llama-3-chat`
48
+
49
+ - Prompt string
50
+
51
+ ```text
52
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
53
+
54
+ {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
55
+
56
+ {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
57
+
58
+ {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
59
+
60
+ {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
61
+ ```
62
+
63
+ - Context size: `128000`
64
+
65
+ - Run as LlamaEdge service
66
+
67
+ ```bash
68
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf \
69
+ llama-api-server.wasm \
70
+ --prompt-template llama-3-chat \
71
+ --ctx-size 128000 \
72
+ --model-name Llama-3.1-70b
73
+ ```
74
+
75
+ - Run as LlamaEdge command app
76
+
77
+ ```bash
78
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf \
79
+ llama-chat.wasm \
80
+ --prompt-template llama-3-chat \
81
+ --ctx-size 128000
82
+ ```
83
+
84
+ ## Quantized GGUF Models
85
+
86
+ | Name | Quant method | Bits | Size | Use case |
87
+ | ---- | ---- | ---- | ---- | ----- |
88
+ | [Meta-Llama-3.1-70B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q2_K.gguf) | Q2_K | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |
89
+ | [Meta-Llama-3.1-70B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |
90
+ | [Meta-Llama-3.1-70B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |
91
+ | [Meta-Llama-3.1-70B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |
92
+ | [Meta-Llama-3.1-70B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 40 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
93
+ | [Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |
94
+ <!-- | [Meta-Llama-3.1-70B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
95
+ | [Meta-Llama-3.1-70B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 50 GB| large, very low quality loss - recommended |
96
+ | [Meta-Llama-3.1-70B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |
97
+ | [Meta-Llama-3.1-70B-Instruct-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q6_K-00001-of-00002.gguf) | Q6_K | 6 | 32.1 GB| very large, extremely low quality loss |
98
+ | [Meta-Llama-3.1-70B-Instruct-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q6_K-00002-of-00002.gguf) | Q6_K | 6 | 25.7 GB| very large, extremely low quality loss |
99
+ | [Meta-Llama-3.1-70B-Instruct-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q8_0-00001-of-00003.gguf) | Q8_0 | 8 | 32 GB| very large, extremely low quality loss - not recommended |
100
+ | [Meta-Llama-3.1-70B-Instruct-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q8_0-00002-of-00003.gguf) | Q8_0 | 8 | 32.1 GB| very large, extremely low quality loss - not recommended |
101
+ | [Meta-Llama-3.1-70B-Instruct-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-Q8_0-00003-of-00003.gguf) | Q8_0 | 8 | 10.9 GB| very large, extremely low quality loss - not recommended |
102
+ | [Meta-Llama-3.1-70B-Instruct-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00001-of-00005.gguf) | f16 | 16 | 32.1 GB| |
103
+ | [Meta-Llama-3.1-70B-Instruct-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00002-of-00005.gguf) | f16 | 16 | 32 GB| |
104
+ | [Meta-Llama-3.1-70B-Instruct-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00003-of-00005.gguf) | f16 | 16 | 32 GB| |
105
+ | [Meta-Llama-3.1-70B-Instruct-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00004-of-00005.gguf) | f16 | 16 | 31.7 GB| |
106
+ | [Meta-Llama-3.1-70B-Instruct-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Meta-Llama-3.1-70B-Instruct-GGUF/blob/main/Meta-Llama-3.1-70B-Instruct-f16-00005-of-00005.gguf) | f16 | 16 | 13.1 GB| | -->
107
+
108
+ *Quantized with llama.cpp 3445.*