schmidt-sebastian commited on
Commit
832fd94
·
0 Parent(s):

Initial upload of MediaPipe-TextEmbedder-Universal-Sentence-Encoder from MediaPipe Solutions

Browse files
Files changed (3) hide show
  1. .gitattributes +38 -0
  2. README.md +122 -0
  3. universal_sentence_encoder.tflite +3 -0
.gitattributes ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.litertlm filter=lfs diff=lfs merge=lfs -text
12
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
13
+ *.model filter=lfs diff=lfs merge=lfs -text
14
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
15
+ *.npy filter=lfs diff=lfs merge=lfs -text
16
+ *.npz filter=lfs diff=lfs merge=lfs -text
17
+ *.onnx filter=lfs diff=lfs merge=lfs -text
18
+ *.ot filter=lfs diff=lfs merge=lfs -text
19
+ *.parquet filter=lfs diff=lfs merge=lfs -text
20
+ *.pb filter=lfs diff=lfs merge=lfs -text
21
+ *.pdf filter=lfs diff=lfs merge=lfs -text
22
+ *.pickle filter=lfs diff=lfs merge=lfs -text
23
+ *.pkl filter=lfs diff=lfs merge=lfs -text
24
+ *.pt filter=lfs diff=lfs merge=lfs -text
25
+ *.pth filter=lfs diff=lfs merge=lfs -text
26
+ *.rar filter=lfs diff=lfs merge=lfs -text
27
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
28
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
29
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
30
+ *.tar filter=lfs diff=lfs merge=lfs -text
31
+ *.task filter=lfs diff=lfs merge=lfs -text
32
+ *.tflite filter=lfs diff=lfs merge=lfs -text
33
+ *.tgz filter=lfs diff=lfs merge=lfs -text
34
+ *.wasm filter=lfs diff=lfs merge=lfs -text
35
+ *.xz filter=lfs diff=lfs merge=lfs -text
36
+ *.zip filter=lfs diff=lfs merge=lfs -text
37
+ *.zst filter=lfs diff=lfs merge=lfs -text
38
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,122 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: litert
4
+ pipeline_tag: sentence-similarity
5
+ language:
6
+ - en
7
+ tags:
8
+ - mediapipe
9
+ - litert
10
+ - tflite
11
+ - sentence-similarity
12
+ - on-device
13
+ - android
14
+ - ios
15
+ - web
16
+ - python
17
+ - flutter
18
+ - nlp
19
+ - sentence-embeddings
20
+ - universal-sentence-encoder
21
+ - dual-encoder
22
+ - fp32
23
+ ---
24
+
25
+ # MediaPipe Universal Sentence Encoder (Text Embedder)
26
+
27
+ Compact dual-encoder text embedding model (`universal_sentence_encoder.tflite`, 6.1 MB, FP32) mapping text inputs to **100-dimensional** dense semantic vectors for rapid on-device cosine similarity and topical clustering in the [MediaPipe Text Embedder (`TextEmbedder`)](https://developers.google.com/edge/mediapipe/solutions/text/text_embedder) task.
28
+
29
+ <div style="border: 1px solid rgba(59, 130, 246, 0.28); background-color: rgba(59, 130, 246, 0.06); border-radius: 8px; padding: 12px 16px; margin: 16px 0;">
30
+ <p style="margin: 0 0 6px 0;"><strong>Documentation:</strong> <a href="https://developers.google.com/edge/mediapipe/solutions/text/text_embedder">MediaPipe Text Embedder Docs</a></p>
31
+ <p style="margin: 0 0 6px 0;"><strong>Samples:</strong> <a href="https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/text_embedder/android">Android</a> · <a href="https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/text_embedder/ios">iOS</a> · <a href="https://colab.research.google.com/github/google-ai-edge/mediapipe-samples/blob/main/examples/text_embedder/python/text_embedder.ipynb">Python Colab</a> · <a href="https://github.com/google-ai-edge/mediapipe-samples-web/blob/main/src/tasks/text-embedder.ts">Web</a> · <a href="https://github.com/google/flutter-mediapipe/tree/main/samples/text/text_embedder">Flutter</a></p>
32
+ <p style="margin: 0;"><strong>Try live:</strong> <a href="https://google-ai-edge.github.io/mediapipe-samples-web/#/text/text_embedder">Web Demo</a></p>
33
+ </div>
34
+
35
+ Uses a compact dual-encoder architecture trained on question-answer datasets (`[-1, 100]` output vector). Captures topical similarity rather than sentiment polarity (for example, `"I like my phone"` and `"I hate my phone"` produce high similarity because both concern phones).
36
+
37
+ ## Files
38
+
39
+ | File | Precision | Size | SHA-256 |
40
+ |---|---|---:|---|
41
+ | [`universal_sentence_encoder.tflite`](https://huggingface.co/litert-community/MediaPipe-TextEmbedder-Universal-Sentence-Encoder/blob/main/universal_sentence_encoder.tflite) | `float32` | 6.12 MB (6,120,274 B) | `89ad3c74175dd8caa398cc22b657296d94302d20c525c12b58b29420f7249749` |
42
+
43
+ ### Download
44
+
45
+ ```bash
46
+ pip install -U huggingface_hub
47
+ hf download litert-community/MediaPipe-TextEmbedder-Universal-Sentence-Encoder universal_sentence_encoder.tflite --local-dir .
48
+ ```
49
+
50
+ ## Inputs, Outputs, and Model Specifications
51
+
52
+ ### `universal_sentence_encoder.tflite`
53
+
54
+ - Embedded `TFLITE_METADATA`: name `USE-QA TFLite model` · version `1` · author `MediaPipe`
55
+
56
+ | Direction | Tensor | Shape | Type | Notes |
57
+ |---|---|---|---|---|
58
+ | Input | `ParseExample/ParseExampleV2:1` | `[-1]` | `string` | inp_text — Input query text |
59
+ | Input | `ParseExample/ParseExampleV2:2` | `[-1]` | `string` | res_context — Input query text |
60
+ | Input | `ParseExample/ParseExampleV2:3` | `[-1]` | `string` | res_text — Input query text |
61
+ | Output | `Final/EncodeQuery/mul` | `[-1, 100]` | `float32` | query_encoding — query-response similarity. |
62
+ | Output | `Final/EncodeResult/mul` | `[-1, 100]` | `float32` | response_encoding — query-response similarity. |
63
+
64
+ ## Use with MediaPipe Tasks
65
+
66
+ ### Python Quickstart
67
+
68
+ ```bash
69
+ pip install -U mediapipe huggingface_hub
70
+ ```
71
+
72
+ ```python
73
+ import mediapipe as mp
74
+ from huggingface_hub import hf_hub_download
75
+
76
+ model_path = hf_hub_download(repo_id="litert-community/MediaPipe-TextEmbedder-Universal-Sentence-Encoder", filename="universal_sentence_encoder.tflite")
77
+
78
+ BaseOptions = mp.tasks.BaseOptions
79
+ TextEmbedder = mp.tasks.text.TextEmbedder
80
+ TextEmbedderOptions = mp.tasks.text.TextEmbedderOptions
81
+
82
+ options = TextEmbedderOptions(base_options=BaseOptions(model_asset_path=model_path), quantize=True)
83
+ with TextEmbedder.create_from_options(options) as embedder:
84
+ e1 = embedder.embed("It's a charming and affecting journey.").embeddings[0]
85
+ e2 = embedder.embed("What a great and fantastic trip!").embeddings[0]
86
+ print("Cosine similarity:", TextEmbedder.cosine_similarity(e1, e2))
87
+ ```
88
+
89
+ ### Cross-Platform Guides & Samples
90
+
91
+ - **Task overview & options:** [Text Embedder documentation](https://developers.google.com/edge/mediapipe/solutions/text/text_embedder)
92
+ - **Platform setup guides:** [Python](https://developers.google.com/edge/mediapipe/solutions/setup_python) · [Web / JavaScript](https://developers.google.com/edge/mediapipe/solutions/setup_web) · [Android (Kotlin / Java)](https://developers.google.com/edge/mediapipe/solutions/setup_android) · [iOS (Swift)](https://developers.google.com/edge/mediapipe/solutions/setup_ios) · [Flutter (Dart)](https://developers.google.com/edge/mediapipe/solutions/setup_flutter)
93
+ - **Runnable sample apps:** [Web Demo](https://google-ai-edge.github.io/mediapipe-samples-web/#/text/text_embedder) · [Web Source](https://github.com/google-ai-edge/mediapipe-samples-web/blob/main/src/tasks/text-embedder.ts) · [Android](https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/text_embedder/android) · [iOS](https://github.com/google-ai-edge/mediapipe-samples/tree/main/examples/text_embedder/ios) · [Python Notebook](https://colab.research.google.com/github/google-ai-edge/mediapipe-samples/blob/main/examples/text_embedder/python/text_embedder.ipynb) · [Flutter](https://github.com/google/flutter-mediapipe/tree/main/samples/text/text_embedder)
94
+
95
+ ## Latency Benchmarks
96
+
97
+ Average CPU pipeline latency reported by the [Text Embedder documentation](https://developers.google.com/edge/mediapipe/solutions/text/text_embedder#benchmarks):
98
+
99
+ | Model Variant | Device | CPU Latency |
100
+ |---|---|---:|
101
+ | Universal Sentence Encoder | Galaxy S26 Ultra (4 threads) | 10 ms |
102
+
103
+ ## Intended Use, Limitations, and Fairness
104
+
105
+ - **Intended applications:** Lightweight on-device semantic similarity, FAQ/retrieval matching, and topical grouping where minimal size (6.1 MB) and ≈10 ms CPU latency are prioritized over 768D LLM embeddings.
106
+ - **Limitations & considerations:** Dual-encoder trained on QA pairs; for multilingual or instruction-steered retrieval/classification tasks, consider `MediaPipe-TextEmbedder-EmbeddingGemma-300M`. No standalone Google fairness PDF is published for this model on the MediaPipe documentation page.
107
+
108
+ ## Provenance
109
+
110
+ Every model binary in this repository is byte-identical (unmodified FlatBuffer weights and embedded `TFLITE_METADATA` bytes) to the official artifact served by Google from `storage.googleapis.com/mediapipe-models`.
111
+
112
+ | Repo File | Upstream URL | GCS Generation | Upstream `Last-Modified` | Pinned Bucket Version |
113
+ |---|---|---|---|---|
114
+ | `universal_sentence_encoder.tflite` | [`universal_sentence_encoder.tflite`](https://storage.googleapis.com/mediapipe-models/text_embedder/universal_sentence_encoder/float32/latest/universal_sentence_encoder.tflite) | `1682480025114200` | Wed, 26 Apr 2023 03:33:45 GMT | `/1/` |
115
+
116
+ ## License and Citation
117
+
118
+ - License: `apache-2.0` — Distributed under Apache License, Version 2.0 alongside the [MediaPipe](https://github.com/google-ai-edge/mediapipe) release artifacts.
119
+
120
+ ### Citation
121
+
122
+ Architecture linked from the MediaPipe Text Embedder documentation: [`aclanthology.org/2022.emnlp-main.640.pdf`](https://aclanthology.org/2022.emnlp-main.640.pdf).
universal_sentence_encoder.tflite ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89ad3c74175dd8caa398cc22b657296d94302d20c525c12b58b29420f7249749
3
+ size 6120274