v0.38.0

See https://github.com/quic/ai-hub-models/releases/v0.38.0 for changelog.

LICENSE

@@ -0,0 +1,2 @@
+The license of the original trained model can be found at https://falconllm.tii.ae/falcon-terms-and-conditions.html.
+The license for the deployable model files (.tflite, .onnx, .dlc, .bin, etc.) can be found at https://falconllm.tii.ae/falcon-terms-and-conditions.html.

README.md

@@ -0,0 +1,154 @@
+---
+library_name: pytorch
+license: other
+tags:
+- llm
+- generative_ai
+- android
+pipeline_tag: text-generation
+
+---
+
+![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/falcon_v3_7b_instruct/web-assets/model_demo.png)
+
+# Falcon3-7B-Instruct: Optimized for Mobile Deployment
+## State-of-the-art large language model useful on a variety of language understanding and generation tasks
+
+
+Falcon3 family of Open Foundation Models is a set of pretrained and instruct LLMs ranging from 1B to 10B.
+
+This model is an implementation of Falcon3-7B-Instruct found [here](https://huggingface.co/tiiuae/Falcon3-7B-Instruct).
+
+
+This repository provides scripts to run Falcon3-7B-Instruct on Qualcomm® devices.
+More details on model performance across various devices, can be found
+[here](https://aihub.qualcomm.com/models/falcon_v3_7b_instruct).
+
+
+
+### Model Details
+
+- **Model Type:** Model_use_case.text_generation
+- **Model Stats:**
+  - Input sequence length for Prompt Processor: 128
+  - Context length: 4096
+  - Precision: w4a16 + w8a16 (few layers)
+  - Num of key-value heads: 4
+  - Model-1 (Prompt Processor): PromptProcessor
+  - Prompt processor input: 128 tokens + position embeddings + attention mask + KV cache inputs
+  - Prompt processor output: 128 output tokens + KV cache outputs
+  - Model-2 (Token Generator): TokenGenerator
+  - Token generator input: 1 input token + position embeddings + attention mask + KV cache inputs
+  - Token generator output: 1 output token + KV cache outputs
+  - Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
+  - Supported languages: English, French, Spanish, Portuguese.
+  - Minimum QNN SDK version required: 2.28.2
+  - TTFT: Time To First Token is the time it takes to generate the first response token. This is expressed as a range because it varies based on the length of the prompt. The lower bound is for a short prompt (up to 128 tokens, i.e., one iteration of the prompt processor) and the upper bound is for a prompt using the full context length (4096 tokens).
+  - Response Rate: Rate of response generation after the first response token.
+
+| Model | Precision | Device | Chipset | Target Runtime | Response Rate (tokens per second) | Time To First Token (range, seconds)
+|---|---|---|---|---|---|
+| Falcon3-7B-Instruct | w4a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | GENIE | 14.02985 | 0.1265205 - 4.048656 | -- | Use Export Script |
+| Falcon3-7B-Instruct | w4a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | GENIE | 9.96829 | 0.1973798 - 6.3161536 | -- | Use Export Script |
+
+## Deploying Falcon3-7B-Instruct on-device
+
+Please follow the [LLM on-device deployment](https://github.com/quic/ai-hub-apps/tree/main/tutorials/llm_on_genie) tutorial.
+
+
+
+## Installation
+
+
+Install the package via pip:
+```bash
+pip install "qai-hub-models[falcon-v3-7b-instruct]"
+```
+
+
+## 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.falcon_v3_7b_instruct.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.falcon_v3_7b_instruct.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.falcon_v3_7b_instruct.export
+```
+
+
+
+
+
+
+## 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 Falcon3-7B-Instruct's performance across various devices [here](https://aihub.qualcomm.com/models/falcon_v3_7b_instruct).
+Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+
+
+## License
+* The license for the original implementation of Falcon3-7B-Instruct can be found
+  [here](https://falconllm.tii.ae/falcon-terms-and-conditions.html).
+* The license for the compiled assets for on-device deployment can be found [here](https://falconllm.tii.ae/falcon-terms-and-conditions.html)
+
+
+
+## References
+* [Source Model Implementation](https://huggingface.co/tiiuae/Falcon3-7B-Instruct)
+
+
+
+## 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:[email protected]).
+
+