Hugging Face's logo

second-state
/
Llama-3.3-70B-Instruct-GGUF

Text Generation
Transformers
GGUF
PyTorch
llama
facebook
meta
llama-3
Inference Endpoints
conversational
Model card Files Community
apepkuss79 commited on
Commit
7e03649
•
1 Parent(s): 5aaa0a2

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +105 -1
README.md CHANGED
@@ -1,3 +1,107 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: llama3.3
3
+ model_name: Llama-3.3-70B-Instruct
4
+ base_model: meta-llama/Llama-3.3-70B-Instruct
5
+ model_creator: meta-llama
6
+ pipeline_tag: text-generation
7
+ quantized_by: Second State Inc.
8
+ library_name: transformers
9
+ language:
10
+ - en
11
+ - fr
12
+ - it
13
+ - pt
14
+ - hi
15
+ - es
16
+ - th
17
+ - de
18
+ tags:
19
+ - facebook
20
+ - meta
21
+ - pytorch
22
+ - llama
23
+ - llama-3
24
  ---
25
+
26
+ <!-- header start -->
27
+ <!-- 200823 -->
28
+ <div style="width: auto; margin-left: auto; margin-right: auto">
29
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
30
+ </div>
31
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
32
+ <!-- header end -->
33
+
34
+ # Llama-3.3-70B-Instruct-GGUF
35
+
36
+ ## Original Model
37
+
38
+ [meta-llama/Llama-3.3-70B-Instruct](https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct)
39
+
40
+ ## Run with LlamaEdge
41
+
42
+ - LlamaEdge version: [v0.14.17](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.17) and above
43
+
44
+ - Prompt template
45
+
46
+ - Prompt type: `llama-3-chat`
47
+
48
+ - Prompt string
49
+
50
+ ```text
51
+ <|begin_of_text|><|start_header_id|>system<|end_header_id|>
52
+
53
+ {{ system_prompt }}<|eot_id|><|start_header_id|>user<|end_header_id|>
54
+
55
+ {{ user_message_1 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
56
+
57
+ {{ model_answer_1 }}<|eot_id|><|start_header_id|>user<|end_header_id|>
58
+
59
+ {{ user_message_2 }}<|eot_id|><|start_header_id|>assistant<|end_header_id|>
60
+ ```
61
+
62
+ - Context size: `128000`
63
+
64
+ - Run as LlamaEdge service
65
+
66
+ ```bash
67
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.3-70B-Instruct-Q5_K_M.gguf \
68
+ llama-api-server.wasm \
69
+ --prompt-template llama-3-chat \
70
+ --ctx-size 128000 \
71
+ --model-name Llama-3-70b
72
+ ```
73
+
74
+ - Run as LlamaEdge command app
75
+
76
+ ```bash
77
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Llama-3.3-70B-Instruct-Q5_K_M.gguf \
78
+ llama-chat.wasm \
79
+ --prompt-template llama-3-chat \
80
+ --ctx-size 128000
81
+ ```
82
+
83
+ <!-- ## Quantized GGUF Models
84
+
85
+ | Name | Quant method | Bits | Size | Use case |
86
+ | ---- | ---- | ---- | ---- | ----- |
87
+ | [Llama-3.3-70B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q2_K.gguf) | Q2_K | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |
88
+ | [Llama-3.3-70B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |
89
+ | [Llama-3.3-70B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |
90
+ | [Llama-3.3-70B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |
91
+ | [Llama-3.3-70B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 40 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
92
+ | [Llama-3.3-70B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |
93
+ | [Llama-3.3-70B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
94
+ | [Llama-3.3-70B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 50 GB| large, very low quality loss - recommended |
95
+ | [Llama-3.3-70B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |
96
+ | [Llama-3.3-70B-Instruct-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q6_K-00001-of-00002.gguf) | Q6_K | 6 | 32.1 GB| very large, extremely low quality loss |
97
+ | [Llama-3.3-70B-Instruct-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q6_K-00002-of-00002.gguf) | Q6_K | 6 | 25.7 GB| very large, extremely low quality loss |
98
+ | [Llama-3.3-70B-Instruct-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q8_0-00001-of-00003.gguf) | Q8_0 | 8 | 32 GB| very large, extremely low quality loss - not recommended |
99
+ | [Llama-3.3-70B-Instruct-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q8_0-00002-of-00003.gguf) | Q8_0 | 8 | 32.1 GB| very large, extremely low quality loss - not recommended |
100
+ | [Llama-3.3-70B-Instruct-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-Q8_0-00003-of-00003.gguf) | Q8_0 | 8 | 10.9 GB| very large, extremely low quality loss - not recommended |
101
+ | [Llama-3.3-70B-Instruct-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-f16-00001-of-00005.gguf) | f16 | 16 | 32.1 GB| |
102
+ | [Llama-3.3-70B-Instruct-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-f16-00002-of-00005.gguf) | f16 | 16 | 32 GB| |
103
+ | [Llama-3.3-70B-Instruct-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-f16-00003-of-00005.gguf) | f16 | 16 | 32 GB| |
104
+ | [Llama-3.3-70B-Instruct-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-f16-00004-of-00005.gguf) | f16 | 16 | 31.7 GB| |
105
+ | [Llama-3.3-70B-Instruct-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Llama-3.3-70B-Instruct-GGUF/blob/main/Llama-3.3-70B-Instruct-f16-00005-of-00005.gguf) | f16 | 16 | 13.1 GB| | -->
106
+
107
+ *Quantized with llama.cpp b4273.*