Hugging Face's logo

second-state
/
Reflection-Llama-3.1-70B-GGUF

Text Generation
Transformers
GGUF
llama
conversational
Model card Files Community
1
apepkuss79 commited on
Commit
0a3664a
·
verified ·
1 Parent(s): e02612f

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: Reflection-Llama-3.1-70B
4
+ base_model: mattshumer/ref_70_e3
5
+ inference: false
6
+ model_creator: Meta Llama3
7
+ model_type: llama
8
+ pipeline_tag: text-generation
9
+ library_name: transformers
10
+ quantized_by: Second State Inc.
11
  ---
12
+
13
+ <!-- header start -->
14
+ <!-- 200823 -->
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
+ </div>
18
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
19
+ <!-- header end -->
20
+
21
+ # Reflection-Llama-3.1-70B-GGUF
22
+
23
+ ## Original Model
24
+
25
+ [mattshumer/ref_70_e3](https://huggingface.co/mattshumer/ref_70_e3)
26
+
27
+ - The recommended system prompt for this model
28
+
29
+ ```text
30
+ You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.
31
+ ```
32
+
33
+ - Tips for performance
34
+
35
+ - Recommended `temperature`: `0.5`
36
+ - Recommended `top_p`: `0.95`
37
+ - For increased accuracy, append `Think carefully.` at the end of your messages.
38
+
39
+
40
+ ## Run with LlamaEdge
41
+
42
+ - LlamaEdge version: [v0.12.4](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.12.4) 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:Reflection-Llama-3.1-70B-Q5_K_M.gguf \
68
+ llama-api-server.wasm \
69
+ --prompt-template llama-3-chat \
70
+ --ctx-size 128000 \
71
+ --model-name Llama-3.1-70b
72
+ ```
73
+
74
+ - Run as LlamaEdge command app
75
+
76
+ ```bash
77
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:Reflection-Llama-3.1-70B-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
+ | [Reflection-Llama-3.1-70B-Q2_K.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q2_K.gguf) | Q2_K | 2 | 26.4 GB| smallest, significant quality loss - not recommended for most purposes |
88
+ | [Reflection-Llama-3.1-70B-Q3_K_L.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q3_K_L.gguf) | Q3_K_L | 3 | 37.1 GB| small, substantial quality loss |
89
+ | [Reflection-Llama-3.1-70B-Q3_K_M.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q3_K_M.gguf) | Q3_K_M | 3 | 34.3 GB| very small, high quality loss |
90
+ | [Reflection-Llama-3.1-70B-Q3_K_S.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q3_K_S.gguf) | Q3_K_S | 3 | 30.9 GB| very small, high quality loss |
91
+ | [Reflection-Llama-3.1-70B-Q4_0.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q4_0.gguf) | Q4_0 | 4 | 40 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
92
+ | [Reflection-Llama-3.1-70B-Q4_K_M.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q4_K_M.gguf) | Q4_K_M | 4 | 42.5 GB| medium, balanced quality - recommended |
93
+ | [Reflection-Llama-3.1-70B-Q4_K_S.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q4_K_S.gguf) | Q4_K_S | 4 | 40.3 GB| small, greater quality loss |
94
+ | [Reflection-Llama-3.1-70B-Q5_0.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q5_0.gguf) | Q5_0 | 5 | 48.7 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
95
+ | [Reflection-Llama-3.1-70B-Q5_K_M.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q5_K_M.gguf) | Q5_K_M | 5 | 49.9 GB| large, very low quality loss - recommended |
96
+ | [Reflection-Llama-3.1-70B-Q5_K_S.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q5_K_S.gguf) | Q5_K_S | 5 | 48.7 GB| large, low quality loss - recommended |
97
+ | [Reflection-Llama-3.1-70B-Q6_K-00001-of-00002.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q6_K-00001-of-00002.gguf) | Q6_K | 6 | 29.8 GB| very large, extremely low quality loss |
98
+ | [Reflection-Llama-3.1-70B-Q6_K-00002-of-00002.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q6_K-00002-of-00002.gguf) | Q6_K | 6 | 28.0 GB| very large, extremely low quality loss |
99
+ | [Reflection-Llama-3.1-70B-Q8_0-00001-of-00003.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q8_0-00001-of-00003.gguf) | Q8_0 | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |
100
+ | [Reflection-Llama-3.1-70B-Q8_0-00002-of-00003.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q8_0-00002-of-00003.gguf) | Q8_0 | 8 | 29.8 GB| very large, extremely low quality loss - not recommended |
101
+ | [Reflection-Llama-3.1-70B-Q8_0-00003-of-00003.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-Q8_0-00003-of-00003.gguf) | Q8_0 | 8 | 15.4 GB| very large, extremely low quality loss - not recommended |
102
+ | [Reflection-Llama-3.1-70B-f16-00001-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00001-of-00005.gguf) | f16 | 16 | 30.0 GB| |
103
+ | [Reflection-Llama-3.1-70B-f16-00002-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00002-of-00005.gguf) | f16 | 16 | 29.6 GB| |
104
+ | [Reflection-Llama-3.1-70B-f16-00003-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00003-of-00005.gguf) | f16 | 16 | 29.6 GB| |
105
+ | [Reflection-Llama-3.1-70B-f16-00004-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00004-of-00005.gguf) | f16 | 16 | 29.6 GB| |
106
+ | [Reflection-Llama-3.1-70B-f16-00005-of-00005.gguf](https://huggingface.co/second-state/Reflection-Llama-3.1-70B-GGUF/blob/main/Reflection-Llama-3.1-70B-f16-00005-of-00005.gguf) | f16 | 16 | 22.2 GB| |
107
+
108
+ *Quantized with llama.cpp 3664.*