Hugging Face's logo

qualcomm
/
Nomic-Embed-Text

Text Generation
PyTorch
android
Model card Files
xet
Community
qaihm-bot commited on
Commit
10ee0ce
·
verified ·
1 Parent(s): 71a7eb6

v0.46.1

Browse files

See https://github.com/quic/ai-hub-models/releases/v0.46.1 for changelog.

Files changed (5) hide show
  1. Nomic-Embed-Text_float.dlc +0 -3
  2. Nomic-Embed-Text_float.onnx.zip +0 -3
  3. Nomic-Embed-Text_float.tflite +0 -3
  4. README.md +73 -227
  5. tool-versions.yaml +0 -4
Nomic-Embed-Text_float.dlc DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b982f6f1947011ebd6d1dda89fb169206e8bf499c8d666c9688f1422111ea42a
3
- size 548667644
 
 
 
 
Nomic-Embed-Text_float.onnx.zip DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:17d88ba59e482fafda49569950da134cce5742d6167a10ec59538fe9bf49ec87
3
- size 507828819
 
 
 
 
Nomic-Embed-Text_float.tflite DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:c09d529e5910d15029199f4780bf2c22260484673836cae1f1bdbe4fd2baea4e
3
- size 547919240
 
 
 
 
README.md CHANGED
@@ -9,245 +9,91 @@ pipeline_tag: text-generation
9
 
10
  ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/web-assets/model_demo.png)
11
 
12
- # Nomic-Embed-Text: Optimized for Mobile Deployment
13
- ## Resizable Production Embeddings
14
-
15
 
16
  A text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks.
17
 
18
- This model is an implementation of Nomic-Embed-Text found [here](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5).
19
-
20
-
21
- This repository provides scripts to run Nomic-Embed-Text on Qualcomm® devices.
22
- More details on model performance across various devices, can be found
23
- [here](https://aihub.qualcomm.com/models/nomic_embed_text).
24
-
25
-
26
-
27
- ### Model Details
28
-
29
- - **Model Type:** Model_use_case.text_generation
30
- - **Model Stats:**
31
- - Model checkpoint: v1.5
32
- - Input resolution: 1x128 (seqlen can vary)
33
- - Number of parameters: 137M
34
- - Model size (float): 523 MB
35
-
36
- | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
37
- |---|---|---|---|---|---|---|---|---|
38
- | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 28.353 ms | 0 - 479 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
39
- | Nomic-Embed-Text | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 28.219 ms | 0 - 478 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
40
- | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 11.195 ms | 0 - 496 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
41
- | Nomic-Embed-Text | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 10.833 ms | 0 - 495 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
42
- | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.412 ms | 0 - 3 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
43
- | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 7.535 ms | 0 - 3 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
44
- | Nomic-Embed-Text | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | ONNX | 8.46 ms | 0 - 3 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
45
- | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 44.631 ms | 0 - 479 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
46
- | Nomic-Embed-Text | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 9.86 ms | 0 - 479 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
47
- | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 28.353 ms | 0 - 479 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
48
- | Nomic-Embed-Text | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 28.219 ms | 0 - 478 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
49
- | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 11.011 ms | 0 - 495 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
50
- | Nomic-Embed-Text | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 10.8 ms | 0 - 470 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
51
- | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 44.631 ms | 0 - 479 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
52
- | Nomic-Embed-Text | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 9.86 ms | 0 - 479 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
53
- | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.457 ms | 0 - 541 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
54
- | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 5.266 ms | 0 - 509 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
55
- | Nomic-Embed-Text | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 5.977 ms | 0 - 488 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
56
- | Nomic-Embed-Text | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 4.34 ms | 0 - 474 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
57
- | Nomic-Embed-Text | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | QNN_DLC | 4.193 ms | 0 - 479 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
58
- | Nomic-Embed-Text | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | ONNX | 4.763 ms | 0 - 458 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
59
- | Nomic-Embed-Text | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | TFLITE | 3.864 ms | 0 - 474 MB | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
60
- | Nomic-Embed-Text | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | QNN_DLC | 3.875 ms | 0 - 475 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
61
- | Nomic-Embed-Text | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | ONNX | 4.382 ms | 0 - 457 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
62
- | Nomic-Embed-Text | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 8.1 ms | 0 - 0 MB | NPU | [Nomic-Embed-Text.dlc](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.dlc) |
63
- | Nomic-Embed-Text | float | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 8.935 ms | 263 - 263 MB | NPU | [Nomic-Embed-Text.onnx.zip](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.onnx.zip) |
64
-
65
-
66
-
67
-
68
- ## Installation
69
-
70
-
71
- Install the package via pip:
72
- ```bash
73
- # NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
74
- pip install "qai-hub-models[nomic-embed-text]"
75
- ```
76
-
77
-
78
- ## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
79
-
80
- Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
81
- Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
82
-
83
- With this API token, you can configure your client to run models on the cloud
84
- hosted devices.
85
- ```bash
86
- qai-hub configure --api_token API_TOKEN
87
- ```
88
- Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
89
-
90
-
91
-
92
- ## Demo off target
93
-
94
- The package contains a simple end-to-end demo that downloads pre-trained
95
- weights and runs this model on a sample input.
96
-
97
- ```bash
98
- python -m qai_hub_models.models.nomic_embed_text.demo
99
- ```
100
-
101
- The above demo runs a reference implementation of pre-processing, model
102
- inference, and post processing.
103
-
104
- **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
105
- environment, please add the following to your cell (instead of the above).
106
- ```
107
- %run -m qai_hub_models.models.nomic_embed_text.demo
108
- ```
109
-
110
-
111
- ### Run model on a cloud-hosted device
112
-
113
- In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
114
- device. This script does the following:
115
- * Performance check on-device on a cloud-hosted device
116
- * Downloads compiled assets that can be deployed on-device for Android.
117
- * Accuracy check between PyTorch and on-device outputs.
118
-
119
- ```bash
120
- python -m qai_hub_models.models.nomic_embed_text.export
121
- ```
122
-
123
-
124
-
125
- ## How does this work?
126
-
127
- This [export script](https://aihub.qualcomm.com/models/nomic_embed_text/qai_hub_models/models/Nomic-Embed-Text/export.py)
128
- leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
129
- on-device. Lets go through each step below in detail:
130
-
131
- Step 1: **Compile model for on-device deployment**
132
-
133
- To compile a PyTorch model for on-device deployment, we first trace the model
134
- in memory using the `jit.trace` and then call the `submit_compile_job` API.
135
-
136
- ```python
137
- import torch
138
-
139
- import qai_hub as hub
140
- from qai_hub_models.models.nomic_embed_text import Model
141
-
142
- # Load the model
143
- torch_model = Model.from_pretrained()
144
-
145
- # Device
146
- device = hub.Device("Samsung Galaxy S25")
147
-
148
- # Trace model
149
- input_shape = torch_model.get_input_spec()
150
- sample_inputs = torch_model.sample_inputs()
151
-
152
- pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
153
-
154
- # Compile model on a specific device
155
- compile_job = hub.submit_compile_job(
156
- model=pt_model,
157
- device=device,
158
- input_specs=torch_model.get_input_spec(),
159
- )
160
-
161
- # Get target model to run on-device
162
- target_model = compile_job.get_target_model()
163
-
164
- ```
165
-
166
-
167
- Step 2: **Performance profiling on cloud-hosted device**
168
-
169
- After compiling models from step 1. Models can be profiled model on-device using the
170
- `target_model`. Note that this scripts runs the model on a device automatically
171
- provisioned in the cloud. Once the job is submitted, you can navigate to a
172
- provided job URL to view a variety of on-device performance metrics.
173
- ```python
174
- profile_job = hub.submit_profile_job(
175
- model=target_model,
176
- device=device,
177
- )
178
-
179
- ```
180
-
181
- Step 3: **Verify on-device accuracy**
182
-
183
- To verify the accuracy of the model on-device, you can run on-device inference
184
- on sample input data on the same cloud hosted device.
185
- ```python
186
- input_data = torch_model.sample_inputs()
187
- inference_job = hub.submit_inference_job(
188
- model=target_model,
189
- device=device,
190
- inputs=input_data,
191
- )
192
- on_device_output = inference_job.download_output_data()
193
-
194
- ```
195
- With the output of the model, you can compute like PSNR, relative errors or
196
- spot check the output with expected output.
197
-
198
- **Note**: This on-device profiling and inference requires access to Qualcomm®
199
- AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
200
-
201
-
202
-
203
- ## Run demo on a cloud-hosted device
204
-
205
- You can also run the demo on-device.
206
-
207
- ```bash
208
- python -m qai_hub_models.models.nomic_embed_text.demo --eval-mode on-device
209
- ```
210
-
211
- **NOTE**: If you want running in a Jupyter Notebook or Google Colab like
212
- environment, please add the following to your cell (instead of the above).
213
- ```
214
- %run -m qai_hub_models.models.nomic_embed_text.demo -- --eval-mode on-device
215
- ```
216
-
217
-
218
- ## Deploying compiled model to Android
219
-
220
-
221
- The models can be deployed using multiple runtimes:
222
- - TensorFlow Lite (`.tflite` export): [This
223
- tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
224
- guide to deploy the .tflite model in an Android application.
225
-
226
-
227
- - QNN (`.so` export ): This [sample
228
- app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
229
- provides instructions on how to use the `.so` shared library in an Android application.
230
-
231
-
232
- ## View on Qualcomm® AI Hub
233
- Get more details on Nomic-Embed-Text's performance across various devices [here](https://aihub.qualcomm.com/models/nomic_embed_text).
234
- Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
235
-
236
 
237
  ## License
238
  * The license for the original implementation of Nomic-Embed-Text can be found
239
  [here](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
240
 
241
-
242
-
243
  ## References
244
  * [Introducing Nomic Embed: A Truly Open Embedding Model](https://www.nomic.ai/blog/posts/nomic-embed-text-v1)
245
  * [Source Model Implementation](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5)
246
 
247
-
248
-
249
  ## Community
250
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
251
  * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
252
-
253
-
 
9
 
10
  ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/web-assets/model_demo.png)
11
 
12
+ # Nomic-Embed-Text: Optimized for Qualcomm Devices
 
 
13
 
14
  A text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks.
15
 
16
+ This is based on the implementation of Nomic-Embed-Text found [here](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5).
17
+ This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/nomic_embed_text) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
18
+
19
+ Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.com) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.
20
+
21
+ ## Getting Started
22
+ There are two ways to deploy this model on your device:
23
+
24
+ ### Option 1: Download Pre-Exported Models
25
+
26
+ Below are pre-exported model assets ready for deployment.
27
+
28
+ | Runtime | Precision | Chipset | SDK Versions | Download |
29
+ |---|---|---|---|---|
30
+ | ONNX | float | Universal | QAIRT 2.37, ONNX Runtime 1.23.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/releases/v0.46.1/nomic_embed_text-onnx-float.zip)
31
+ | QNN_DLC | float | Universal | QAIRT 2.42 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/releases/v0.46.1/nomic_embed_text-qnn_dlc-float.zip)
32
+ | TFLITE | float | Universal | QAIRT 2.42, TFLite 2.17.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/releases/v0.46.1/nomic_embed_text-tflite-float.zip)
33
+
34
+ For more device-specific assets and performance metrics, visit **[Nomic-Embed-Text on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/nomic_embed_text)**.
35
+
36
+
37
+ ### Option 2: Export with Custom Configurations
38
+
39
+ Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/nomic_embed_text) Python library to compile and export the model with your own:
40
+ - Custom weights (e.g., fine-tuned checkpoints)
41
+ - Custom input shapes
42
+ - Target device and runtime configurations
43
+
44
+ This option is ideal if you need to customize the model beyond the default configuration provided here.
45
+
46
+ See our repository for [Nomic-Embed-Text on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/nomic_embed_text) for usage instructions.
47
+
48
+ ## Model Details
49
+
50
+ **Model Type:** Model_use_case.text_generation
51
+
52
+ **Model Stats:**
53
+ - Model checkpoint: v1.5
54
+ - Input resolution: 1x128 (seqlen can vary)
55
+ - Number of parameters: 137M
56
+ - Model size (float): 523 MB
57
+
58
+ ## Performance Summary
59
+ | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
60
+ |---|---|---|---|---|---|---
61
+ | Nomic-Embed-Text | ONNX | float | Snapdragon® X Elite | 8.962 ms | 263 - 263 MB | NPU
62
+ | Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.925 ms | 0 - 488 MB | NPU
63
+ | Nomic-Embed-Text | ONNX | float | Qualcomm® QCS8550 (Proxy) | 8.472 ms | 0 - 323 MB | NPU
64
+ | Nomic-Embed-Text | ONNX | float | Qualcomm® QCS9075 | 11.424 ms | 0 - 4 MB | NPU
65
+ | Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.75 ms | 0 - 457 MB | NPU
66
+ | Nomic-Embed-Text | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.317 ms | 0 - 455 MB | NPU
67
+ | Nomic-Embed-Text | QNN_DLC | float | Snapdragon® X Elite | 8.101 ms | 0 - 0 MB | NPU
68
+ | Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.317 ms | 0 - 446 MB | NPU
69
+ | Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 28.402 ms | 0 - 415 MB | NPU
70
+ | Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.624 ms | 0 - 3 MB | NPU
71
+ | Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8775P | 9.771 ms | 0 - 415 MB | NPU
72
+ | Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS9075 | 10.408 ms | 2 - 4 MB | NPU
73
+ | Nomic-Embed-Text | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 10.925 ms | 0 - 427 MB | NPU
74
+ | Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA7255P | 28.402 ms | 0 - 415 MB | NPU
75
+ | Nomic-Embed-Text | QNN_DLC | float | Qualcomm® SA8295P | 10.716 ms | 0 - 399 MB | NPU
76
+ | Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.236 ms | 0 - 414 MB | NPU
77
+ | Nomic-Embed-Text | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.824 ms | 0 - 413 MB | NPU
78
+ | Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.297 ms | 0 - 459 MB | NPU
79
+ | Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 28.35 ms | 0 - 425 MB | NPU
80
+ | Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.407 ms | 0 - 3 MB | NPU
81
+ | Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8775P | 9.726 ms | 0 - 424 MB | NPU
82
+ | Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS9075 | 10.607 ms | 0 - 265 MB | NPU
83
+ | Nomic-Embed-Text | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 10.925 ms | 0 - 429 MB | NPU
84
+ | Nomic-Embed-Text | TFLITE | float | Qualcomm® SA7255P | 28.35 ms | 0 - 425 MB | NPU
85
+ | Nomic-Embed-Text | TFLITE | float | Qualcomm® SA8295P | 10.787 ms | 0 - 403 MB | NPU
86
+ | Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.22 ms | 0 - 426 MB | NPU
87
+ | Nomic-Embed-Text | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.827 ms | 0 - 421 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
 
89
  ## License
90
  * The license for the original implementation of Nomic-Embed-Text can be found
91
  [here](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
92
 
 
 
93
  ## References
94
  * [Introducing Nomic Embed: A Truly Open Embedding Model](https://www.nomic.ai/blog/posts/nomic-embed-text-v1)
95
  * [Source Model Implementation](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5)
96
 
 
 
97
  ## Community
98
  * Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
99
  * For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
 
 
tool-versions.yaml DELETED
@@ -1,4 +0,0 @@
1
- tool_versions:
2
- onnx:
3
- qairt: 2.37.1.250807093845_124904
4
- onnx_runtime: 1.23.0