Hugging Face's logo

second-state
/
datagemma-rig-27b-it-GGUF

Text Generation
Transformers
GGUF
gemma2
conversational
Model card Files Community
apepkuss79 commited on
Commit
29efeec
·
verified ·
1 Parent(s): e50d883

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +84 -1
README.md CHANGED
@@ -1,3 +1,86 @@
1
  ---
2
- license: apache-2.0
 
 
 
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ base_model: google/datagemma-rig-27b-it
3
+ inference: false
4
+ license: gemma
5
+ library_name: transformers
6
+ pipeline_tag: text-generation
7
+ model_creator: Google
8
+ model_name: datagemma-rig-27b-it
9
+ quantized_by: Second State Inc.
10
+ tags:
11
+ - conversational
12
  ---
13
+
14
+ <!-- header start -->
15
+ <!-- 200823 -->
16
+ <div style="width: auto; margin-left: auto; margin-right: auto">
17
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </div>
19
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
20
+ <!-- header end -->
21
+
22
+ # Datagemma-rig-27b-it-GGUF
23
+
24
+ ## Original Model
25
+
26
+ [google/datagemma-rig-27b-it](https://huggingface.co/google/datagemma-rig-27b-it)
27
+
28
+ ## Run with LlamaEdge
29
+
30
+ - LlamaEdge version: [v0.14.3](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.3) and above
31
+
32
+ - Prompt template
33
+
34
+ - Prompt type: `gemma-instruct`
35
+
36
+ - Prompt string
37
+
38
+ ```text
39
+ <bos><start_of_turn>user
40
+ {user_message}<end_of_turn>
41
+ <start_of_turn>model
42
+ {model_message}<end_of_turn>model
43
+ ```
44
+
45
+ - Context size: `8192`
46
+
47
+ - Run as LlamaEdge service
48
+
49
+ ```bash
50
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:datagemma-rig-27b-it-Q5_K_M.gguf \
51
+ llama-api-server.wasm \
52
+ --prompt-template gemma-instruct \
53
+ --ctx-size 8192 \
54
+ --model-name gemma-2-27b
55
+ ```
56
+
57
+ - Run as LlamaEdge command app
58
+
59
+ ```bash
60
+ wasmedge --dir .:. \
61
+ --nn-preload default:GGML:AUTO:datagemma-rig-27b-it-Q5_K_M.gguf \
62
+ llama-chat.wasm \
63
+ --prompt-template gemma-instruct \
64
+ --ctx-size 8192
65
+ ```
66
+
67
+ ## Quantized GGUF Models
68
+
69
+ | Name | Quant method | Bits | Size | Use case |
70
+ | ---- | ---- | ---- | ---- | ----- |
71
+ | [datagemma-rig-27b-it-Q2_K.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q2_K.gguf) | Q2_K | 2 | 10.4 GB| smallest, significant quality loss - not recommended for most purposes |
72
+ | [datagemma-rig-27b-it-Q3_K_L.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q3_K_L.gguf) | Q3_K_L | 3 | 14.5 GB| small, substantial quality loss |
73
+ | [datagemma-rig-27b-it-Q3_K_M.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q3_K_M.gguf) | Q3_K_M | 3 | 13.4 GB| very small, high quality loss |
74
+ | [datagemma-rig-27b-it-Q3_K_S.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q3_K_S.gguf) | Q3_K_S | 3 | 12.2 GB| very small, high quality loss |
75
+ | [datagemma-rig-27b-it-Q4_0.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q4_0.gguf) | Q4_0 | 4 | 15.6 GB| legacy; small, very high quality loss - prefer using Q3_K_M |
76
+ | [datagemma-rig-27b-it-Q4_K_M.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q4_K_M.gguf) | Q4_K_M | 4 | 16.6 GB| medium, balanced quality - recommended |
77
+ | [datagemma-rig-27b-it-Q4_K_S.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q4_K_S.gguf) | Q4_K_S | 4 | 15.7 GB| small, greater quality loss |
78
+ | [datagemma-rig-27b-it-Q5_0.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q5_0.gguf) | Q5_0 | 5 | 18.9 GB| legacy; medium, balanced quality - prefer using Q4_K_M |
79
+ | [datagemma-rig-27b-it-Q5_K_M.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q5_K_M.gguf) | Q5_K_M | 5 | 19.4 GB| large, very low quality loss - recommended |
80
+ | [datagemma-rig-27b-it-Q5_K_S.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q5_K_S.gguf) | Q5_K_S | 5 | 18.9 GB| large, low quality loss - recommended |
81
+ | [datagemma-rig-27b-it-Q6_K.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q6_K.gguf) | Q6_K | 6 | 22.3 GB| very large, extremely low quality loss |
82
+ | [datagemma-rig-27b-it-Q8_0.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-Q8_0.gguf) | Q8_0 | 8 | 28.9 GB| very large, extremely low quality loss - not recommended |
83
+ | [datagemma-rig-27b-it-f16-00001-of-00002.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-f16-00001-of-00002.gguf) | f16 | 16 | 29.9 GB| |
84
+ | [datagemma-rig-27b-it-f16-00002-of-00002.gguf](https://huggingface.co/second-state/datagemma-rig-27b-it-GGUF/blob/main/datagemma-rig-27b-it-f16-00002-of-00002.gguf) | f16 | 16 | 24.6 GB| |
85
+
86
+ *Quantized with llama.cpp b3664*