Hugging Face's logo

second-state
/
embeddinggemma-300m-GGUF

Sentence Similarity
sentence-transformers
GGUF
gemma3_text
Model card Files
xet
 Community
apepkuss79 commited on
Commit
e22086a
·
verified ·
1 Parent(s): f9ae79a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +64 -66
README.md CHANGED
@@ -1,67 +1,65 @@
1
- ---
2
- license: gemma
3
- pipeline_tag: sentence-similarity
4
- library_name: sentence-transformers
5
- base_model: google/embeddinggemma-300m
6
- model_creator: google
7
- model_name: embeddinggemma-300m
8
- quantized_by: Second State Inc.
9
- ---
10
-
11
- <!-- header start -->
12
- <!-- 200823 -->
13
- <div style="width: auto; margin-left: auto; margin-right: auto">
14
- <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
- </div>
16
- <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
17
- <!-- header end -->
18
-
19
- # embeddinggemma-300m-Embedding-GGUF
20
-
21
- ## Original Model
22
-
23
- [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m)
24
-
25
- ## Run with LlamaEdge
26
-
27
- - LlamaEdge version: coming soon
28
-
29
- <!-- - LlamaEdge version: [v0.14.17](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.17) -->
30
-
31
- - Prompt template
32
-
33
- - Prompt type: `embedding`
34
-
35
- - Context size: `2048`
36
-
37
- - Embedding size: `128, 256, 512, 768`
38
-
39
- - Run as LlamaEdge service
40
-
41
- ```bash
42
- wasmedge --dir .:. --nn-preload default:GGML:AUTO:embeddinggemma-300m-f16.gguf \
43
- llama-api-server.wasm \
44
- --prompt-template embedding \
45
- --ctx-size 768 \
46
- --model-name embeddinggemma-300m
47
- ```
48
-
49
- ## Quantized GGUF Models
50
-
51
- | Name | Quant method | Bits | Size | Use case |
52
- | ---- | ---- | ---- | ---- | ----- |
53
- | [embeddinggemma-300m-Q2_K.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q2_K.gguf) | Q2_K | 2 | 212 MB| smallest, significant quality loss - not recommended for most purposes |
54
- | [embeddinggemma-300m-Q3_K_L.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_L.gguf) | Q3_K_L | 3 | 227 MB| small, substantial quality loss |
55
- | [embeddinggemma-300m-Q3_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_M.gguf) | Q3_K_M | 3 | 224 MB| very small, high quality loss |
56
- | [embeddinggemma-300m-Q3_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_S.gguf) | Q3_K_S | 3 | 218 MB| very small, high quality loss |
57
- | [embeddinggemma-300m-Q4_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_0.gguf) | Q4_0 | 4 | 229 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
58
- | [embeddinggemma-300m-Q4_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_K_M.gguf) | Q4_K_M | 4 | 236 MB| medium, balanced quality - recommended |
59
- | [embeddinggemma-300m-Q4_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_K_S.gguf) | Q4_K_S | 4 | 232 MB| small, greater quality loss |
60
- | [embeddinggemma-300m-Q5_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_0.gguf) | Q5_0 | 5 | 242 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
61
- | [embeddinggemma-300m-Q5_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_K_M.gguf) | Q5_K_M | 5 | 247 MB| large, very low quality loss - recommended |
62
- | [embeddinggemma-300m-Q5_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_K_S.gguf) | Q5_K_S | 5 | 243 MB| large, low quality loss - recommended |
63
- | [embeddinggemma-300m-Q6_K.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q6_K.gguf) | Q6_K | 6 | 260 MB| very large, extremely low quality loss |
64
- | [embeddinggemma-300m-Q8_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q8_0.gguf) | Q8_0 | 8 | 329 MB| very large, extremely low quality loss - not recommended |
65
- | [embeddinggemma-300m-f16.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-f16.gguf) | f16 | 16 | 616 MB| very large, extremely low quality loss - not recommended |
66
-
67
  *Quantized with llama.cpp b6397*
 
1
+ ---
2
+ license: gemma
3
+ pipeline_tag: sentence-similarity
4
+ library_name: sentence-transformers
5
+ base_model: google/embeddinggemma-300m
6
+ model_creator: google
7
+ model_name: embeddinggemma-300m
8
+ quantized_by: Second State Inc.
9
+ ---
10
+
11
+ <!-- header start -->
12
+ <!-- 200823 -->
13
+ <div style="width: auto; margin-left: auto; margin-right: auto">
14
+ <img src="https://github.com/LlamaEdge/LlamaEdge/raw/dev/assets/logo.svg" style="width: 100%; min-width: 400px; display: block; margin: auto;">
15
+ </div>
16
+ <hr style="margin-top: 1.0em; margin-bottom: 1.0em;">
17
+ <!-- header end -->
18
+
19
+ # embeddinggemma-300m-Embedding-GGUF
20
+
21
+ ## Original Model
22
+
23
+ [google/embeddinggemma-300m](https://huggingface.co/google/embeddinggemma-300m)
24
+
25
+ ## Run with LlamaEdge
26
+
27
+ - LlamaEdge version: [v0.26.1](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.26.1) and above
28
+
29
+ - Prompt template
30
+
31
+ - Prompt type: `embedding`
32
+
33
+ - Context size: `2048`
34
+
35
+ - Embedding size: `128, 256, 512, 768`
36
+
37
+ - Run as LlamaEdge service
38
+
39
+ ```bash
40
+ wasmedge --dir .:. --nn-preload default:GGML:AUTO:embeddinggemma-300m-f16.gguf \
41
+ llama-api-server.wasm \
42
+ --prompt-template embedding \
43
+ --ctx-size 768 \
44
+ --model-name embeddinggemma-300m
45
+ ```
46
+
47
+ ## Quantized GGUF Models
48
+
49
+ | Name | Quant method | Bits | Size | Use case |
50
+ | ---- | ---- | ---- | ---- | ----- |
51
+ | [embeddinggemma-300m-Q2_K.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q2_K.gguf) | Q2_K | 2 | 212 MB| smallest, significant quality loss - not recommended for most purposes |
52
+ | [embeddinggemma-300m-Q3_K_L.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_L.gguf) | Q3_K_L | 3 | 227 MB| small, substantial quality loss |
53
+ | [embeddinggemma-300m-Q3_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_M.gguf) | Q3_K_M | 3 | 224 MB| very small, high quality loss |
54
+ | [embeddinggemma-300m-Q3_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q3_K_S.gguf) | Q3_K_S | 3 | 218 MB| very small, high quality loss |
55
+ | [embeddinggemma-300m-Q4_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_0.gguf) | Q4_0 | 4 | 229 MB| legacy; small, very high quality loss - prefer using Q3_K_M |
56
+ | [embeddinggemma-300m-Q4_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_K_M.gguf) | Q4_K_M | 4 | 236 MB| medium, balanced quality - recommended |
57
+ | [embeddinggemma-300m-Q4_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q4_K_S.gguf) | Q4_K_S | 4 | 232 MB| small, greater quality loss |
58
+ | [embeddinggemma-300m-Q5_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_0.gguf) | Q5_0 | 5 | 242 MB| legacy; medium, balanced quality - prefer using Q4_K_M |
59
+ | [embeddinggemma-300m-Q5_K_M.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_K_M.gguf) | Q5_K_M | 5 | 247 MB| large, very low quality loss - recommended |
60
+ | [embeddinggemma-300m-Q5_K_S.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q5_K_S.gguf) | Q5_K_S | 5 | 243 MB| large, low quality loss - recommended |
61
+ | [embeddinggemma-300m-Q6_K.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q6_K.gguf) | Q6_K | 6 | 260 MB| very large, extremely low quality loss |
62
+ | [embeddinggemma-300m-Q8_0.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-Q8_0.gguf) | Q8_0 | 8 | 329 MB| very large, extremely low quality loss - not recommended |
63
+ | [embeddinggemma-300m-f16.gguf](https://huggingface.co/second-state/embeddinggemma-300m-Embedding-GGUF/blob/main/embeddinggemma-300m-f16.gguf) | f16 | 16 | 616 MB| very large, extremely low quality loss - not recommended |
64
+
 
 
65
  *Quantized with llama.cpp b6397*