Upload README.md with huggingface_hub

README.md

@@ -0,0 +1,261 @@
+---
+library_name: pytorch
+license: apache-2.0
+tags:
+- android
+pipeline_tag: text-generation
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/nomic_embed_text/web-assets/model_demo.png)
+
+# Nomic-Embed-Text: Optimized for Mobile Deployment
+## Resizable Production Embeddings
+
+
+A text encoder that surpasses OpenAI text-embedding-ada-002 and text-embedding-3-small performance on short and long context tasks.
+
+This model is an implementation of Nomic-Embed-Text found [here](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5).
+
+
+This repository provides scripts to run Nomic-Embed-Text on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/nomic_embed_text).
+
+
+### Model Details
+
+- **Model Type:** Text generation
+- **Model Stats:**
+  - Model checkpoint: v1.5
+  - Input resolution: 1x128 (seqlen can vary)
+  - Number of parameters: 137M
+  - Model size: 547 MB
+
+| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
+|---|---|---|---|---|---|---|---|---|
+| Nomic-Embed-Text | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | TFLITE | 10.558 ms | 0 - 21 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 8.117 ms | 0 - 2 MB | FP16 | NPU | [Nomic-Embed-Text.so](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.so) |
+| Nomic-Embed-Text | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | TFLITE | 7.626 ms | 0 - 406 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 5.848 ms | 0 - 20 MB | FP16 | NPU | [Nomic-Embed-Text.so](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.so) |
+| Nomic-Embed-Text | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | TFLITE | 7.369 ms | 0 - 362 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 6.16 ms | 0 - 324 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | SA7255P ADP | SA7255P | TFLITE | 186.829 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | SA7255P ADP | SA7255P | QNN | 181.788 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | SA8255 (Proxy) | SA8255P Proxy | TFLITE | 10.275 ms | 0 - 20 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | SA8255 (Proxy) | SA8255P Proxy | QNN | 8.125 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | SA8295P ADP | SA8295P | TFLITE | 14.386 ms | 0 - 348 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | SA8295P ADP | SA8295P | QNN | 11.182 ms | 0 - 17 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | SA8650 (Proxy) | SA8650P Proxy | TFLITE | 10.549 ms | 0 - 19 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | SA8650 (Proxy) | SA8650P Proxy | QNN | 8.168 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | SA8775P ADP | SA8775P | TFLITE | 15.481 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | SA8775P ADP | SA8775P | QNN | 12.227 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | QCS8275 (Proxy) | QCS8275 Proxy | TFLITE | 186.829 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 181.788 ms | 0 - 9 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | QCS8550 (Proxy) | QCS8550 Proxy | TFLITE | 10.388 ms | 0 - 18 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 8.06 ms | 0 - 2 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | QCS9075 (Proxy) | QCS9075 Proxy | TFLITE | 15.481 ms | 0 - 360 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 12.227 ms | 0 - 10 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | QCS8450 (Proxy) | QCS8450 Proxy | TFLITE | 12.932 ms | 0 - 401 MB | FP16 | NPU | [Nomic-Embed-Text.tflite](https://huggingface.co/qualcomm/Nomic-Embed-Text/blob/main/Nomic-Embed-Text.tflite) |
+| Nomic-Embed-Text | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 11.278 ms | 0 - 364 MB | FP16 | NPU | Use Export Script |
+| Nomic-Embed-Text | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 8.353 ms | 0 - 0 MB | FP16 | NPU | Use Export Script |
+
+
+
+
+## Installation
+
+
+Install the package via pip:
+```bash
+pip install "qai-hub-models[nomic-embed-text]"
+```
+
+
+## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
+
+Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
+Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
+
+With this API token, you can configure your client to run models on the cloud
+hosted devices.
+```bash
+qai-hub configure --api_token API_TOKEN
+```
+Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
+
+
+
+## Demo off target
+
+The package contains a simple end-to-end demo that downloads pre-trained
+weights and runs this model on a sample input.
+
+```bash
+python -m qai_hub_models.models.nomic_embed_text.demo
+```
+
+The above demo runs a reference implementation of pre-processing, model
+inference, and post processing.
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.nomic_embed_text.demo
+```
+
+
+### Run model on a cloud-hosted device
+
+In addition to the demo, you can also run the model on a cloud-hosted Qualcomm®
+device. This script does the following:
+* Performance check on-device on a cloud-hosted device
+* Downloads compiled assets that can be deployed on-device for Android.
+* Accuracy check between PyTorch and on-device outputs.
+
+```bash
+python -m qai_hub_models.models.nomic_embed_text.export
+```
+```
+Profiling Results
+------------------------------------------------------------
+Nomic-Embed-Text
+Device                          : Samsung Galaxy S23 (13)
+Runtime                         : TFLITE                 
+Estimated inference time (ms)   : 10.6                   
+Estimated peak memory usage (MB): [0, 21]                
+Total # Ops                     : 906                    
+Compute Unit(s)                 : NPU (906 ops)          
+```
+
+
+## How does this work?
+
+This [export script](https://aihub.qualcomm.com/models/nomic_embed_text/qai_hub_models/models/Nomic-Embed-Text/export.py)
+leverages [Qualcomm® AI Hub](https://aihub.qualcomm.com/) to optimize, validate, and deploy this model
+on-device. Lets go through each step below in detail:
+
+Step 1: **Compile model for on-device deployment**
+
+To compile a PyTorch model for on-device deployment, we first trace the model
+in memory using the `jit.trace` and then call the `submit_compile_job` API.
+
+```python
+import torch
+
+import qai_hub as hub
+from qai_hub_models.models.nomic_embed_text import Model
+
+# Load the model
+torch_model = Model.from_pretrained()
+
+# Device
+device = hub.Device("Samsung Galaxy S24")
+
+# Trace model
+input_shape = torch_model.get_input_spec()
+sample_inputs = torch_model.sample_inputs()
+
+pt_model = torch.jit.trace(torch_model, [torch.tensor(data[0]) for _, data in sample_inputs.items()])
+
+# Compile model on a specific device
+compile_job = hub.submit_compile_job(
+    model=pt_model,
+    device=device,
+    input_specs=torch_model.get_input_spec(),
+)
+
+# Get target model to run on-device
+target_model = compile_job.get_target_model()
+
+```
+
+
+Step 2: **Performance profiling on cloud-hosted device**
+
+After compiling models from step 1. Models can be profiled model on-device using the
+`target_model`. Note that this scripts runs the model on a device automatically
+provisioned in the cloud.  Once the job is submitted, you can navigate to a
+provided job URL to view a variety of on-device performance metrics.
+```python
+profile_job = hub.submit_profile_job(
+    model=target_model,
+    device=device,
+)
+        
+```
+
+Step 3: **Verify on-device accuracy**
+
+To verify the accuracy of the model on-device, you can run on-device inference
+on sample input data on the same cloud hosted device.
+```python
+input_data = torch_model.sample_inputs()
+inference_job = hub.submit_inference_job(
+    model=target_model,
+    device=device,
+    inputs=input_data,
+)
+    on_device_output = inference_job.download_output_data()
+
+```
+With the output of the model, you can compute like PSNR, relative errors or
+spot check the output with expected output.
+
+**Note**: This on-device profiling and inference requires access to Qualcomm®
+AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
+
+
+
+## Run demo on a cloud-hosted device
+
+You can also run the demo on-device.
+
+```bash
+python -m qai_hub_models.models.nomic_embed_text.demo --on-device
+```
+
+**NOTE**: If you want running in a Jupyter Notebook or Google Colab like
+environment, please add the following to your cell (instead of the above).
+```
+%run -m qai_hub_models.models.nomic_embed_text.demo -- --on-device
+```
+
+
+## Deploying compiled model to Android
+
+
+The models can be deployed using multiple runtimes:
+- TensorFlow Lite (`.tflite` export): [This
+  tutorial](https://www.tensorflow.org/lite/android/quickstart) provides a
+  guide to deploy the .tflite model in an Android application.
+
+
+- QNN (`.so` export ): This [sample
+  app](https://docs.qualcomm.com/bundle/publicresource/topics/80-63442-50/sample_app.html)
+provides instructions on how to use the `.so` shared library  in an Android application.
+
+
+## View on Qualcomm® AI Hub
+Get more details on Nomic-Embed-Text's performance across various devices [here](https://aihub.qualcomm.com/models/nomic_embed_text).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
+## License
+* The license for the original implementation of Nomic-Embed-Text can be found
+  [here](https://huggingface.co/datasets/choosealicense/licenses/blob/main/markdown/apache-2.0.md).
+* The license for the compiled assets for on-device deployment can be found [here](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/Qualcomm+AI+Hub+Proprietary+License.pdf)
+
+
+
+## References
+* [Introducing Nomic Embed: A Truly Open Embedding Model](https://www.nomic.ai/blog/posts/nomic-embed-text-v1)
+* [Source Model Implementation](https://huggingface.co/nomic-ai/nomic-embed-text-v1.5)
+
+
+
+## Community
+* Join [our AI Hub Slack community](https://aihub.qualcomm.com/community/slack) to collaborate, post questions and learn more about on-device AI.
+* For questions or feedback please [reach out to us](mailto:ai-hub-support@qti.qualcomm.com).
+
+