v0.46.1

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

README.md

@@ -11,140 +11,80 @@ pipeline_tag: text-generation
 
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/llama_v3_2_3b_instruct/web-assets/model_demo.png)
 
-# Llama-v3.2-3B-Instruct: Optimized for Mobile Deployment
-## State-of-the-art large language model useful on a variety of language understanding and generation tasks
-
+# Llama-v3.2-3B-Instruct: Optimized for Qualcomm Devices
 
 Llama 3 is a family of LLMs. The model is quantized to w4a16 (4-bit weights and 16-bit activations) and part of the model is quantized to w8a16 (8-bit weights and 16-bit activations) making it suitable for on-device deployment.
 
-This model is an implementation of Llama-v3.2-3B-Instruct found [here](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/).
-
-
-This repository provides scripts to run Llama-v3.2-3B-Instruct on Qualcomm® devices.
-More details on model performance across various devices, can be found
-[here](https://aihub.qualcomm.com/models/llama_v3_2_3b_instruct).
-
-**WARNING**: The model assets are not readily available for download due to licensing restrictions.
-
-### Model Details
+This is based on the implementation of Llama-v3.2-3B-Instruct found [here](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/).
+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/llama_v3_2_3b_instruct) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
-- **Model Type:** Model_use_case.text_generation
-- **Model Stats:**
-  - Input sequence length for Prompt Processor: 128
-  - Maximum context length: 4096
-  - Precision: w4 + w8 (few layers) with fp16 activations and w4a16 + w8a16 (few layers) are supported
-  - Supported languages: English.
-  - 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)
-|---|---|---|---|---|---|
-| Llama-v3.2-3B-Instruct | w4a16 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | GENIE | 29.48402 | 0.058016 - 1.856531 | -- | -- |
-| Llama-v3.2-3B-Instruct | w4a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | GENIE | 23.4718 | 0.088195 - 2.82225 | -- | -- |
-| Llama-v3.2-3B-Instruct | w4a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | GENIE | 18.4176 | 0.12593600000000002 - 4.029952000000001 | -- | -- |
-| Llama-v3.2-3B-Instruct | w4 | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen 5 Mobile | GENIE | 18.00883 | 0.131546 - 4.209475 | -- | -- |
-| Llama-v3.2-3B-Instruct | w4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | GENIE | 13.83 | 0.088195 - 2.82225 | -- | -- |
-| Llama-v3.2-3B-Instruct | w4 | SA8295P ADP | Qualcomm® SA8295P | GENIE | 3.523 | 0.37311700000000003 - 2.9849360000000003 | -- | -- |
+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.
 
 ## Deploying Llama 3.2 3B on-device
 
 Please follow the [LLM on-device deployment](https://github.com/quic/ai-hub-apps/tree/main/tutorials/llm_on_genie) tutorial.
 
+## Getting Started
+Due to licensing restrictions, we cannot distribute pre-exported model assets for this model.
+Use the [Qualcomm® AI Hub Models](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/llama_v3_2_3b_instruct) Python library to compile and export the model with your own:
+- Custom weights (e.g., fine-tuned checkpoints)
+- Custom input shapes
+- Target device and runtime configurations
 
+See our repository for [Llama-v3.2-3B-Instruct on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/llama_v3_2_3b_instruct) for usage instructions.
 
-## Installation
-
-
-Install the package via pip:
-```bash
-# NOTE: 3.10 <= PYTHON_VERSION < 3.14 is supported.
-pip install "qai-hub-models[llama-v3-2-3b-instruct]"
-```
-
-
-## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
-
-Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.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://workbench.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.llama_v3_2_3b_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.llama_v3_2_3b_instruct.demo
-```
 
+## Model Details
 
-### Run model on a cloud-hosted device
+**Model Type:** Model_use_case.text_generation
 
-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.llama_v3_2_3b_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 Llama-v3.2-3B-Instruct's performance across various devices [here](https://aihub.qualcomm.com/models/llama_v3_2_3b_instruct).
-Explore all available models on [Qualcomm® AI Hub](https://aihub.qualcomm.com/)
+**Model Stats:**
+- Input sequence length for Prompt Processor: 128
+- Maximum context length: 4096
+- Precision: w4 + w8 (few layers) with fp16 activations and w4a16 + w8a16 (few layers) are supported
+- Supported languages: English.
+- 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.
 
+## Performance Summary
+| Model | Runtime | Precision | Chipset | Context Length | Response Rate (tokens per second) | Time To First Token (range, seconds)
+|---|---|---|---|---|---|---
+| Llama-v3.2-3B-Instruct | GENIE | w4 | Snapdragon® 8 Elite Mobile | 4096 | 13.83 | 0.088195 - 2.82225
+| Llama-v3.2-3B-Instruct | GENIE | w4 | Qualcomm® SA8295P | 1024 | 3.523 | 0.37311700000000003 - 2.9849360000000003
+| Llama-v3.2-3B-Instruct | GENIE | w4 | Snapdragon® 8 Elite Gen 5 Mobile | 4096 | 18.00883 | 0.131546 - 4.209475
+| Llama-v3.2-3B-Instruct | GENIE | w4a16 | Snapdragon® 8 Elite Mobile | 4096 | 23.4718 | 0.088195 - 2.82225
+| Llama-v3.2-3B-Instruct | GENIE | w4a16 | Snapdragon® X Elite | 4096 | 18.4176 | 0.12593600000000002 - 4.029952000000001
+| Llama-v3.2-3B-Instruct | GENIE | w4a16 | Snapdragon® 8 Elite Gen 5 Mobile | 4096 | 29.48402 | 0.058016 - 1.856531
 
 ## License
 * The license for the original implementation of Llama-v3.2-3B-Instruct can be found
   [here](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct/blob/main/LICENSE.txt).
 
-
-
 ## References
 * [LLaMA: Open and Efficient Foundation Language Models](https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_2/)
 * [Source Model Implementation](https://huggingface.co/meta-llama/Llama-3.2-3B-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:ai-hub-support@qti.qualcomm.com).
 
-
+## Usage and Limitations
+
+This model may not be used for or in connection with any of the following applications:
+
+- Accessing essential private and public services and benefits;
+- Administration of justice and democratic processes;
+- Assessing or recognizing the emotional state of a person;
+- Biometric and biometrics-based systems, including categorization of persons based on sensitive characteristics;
+- Education and vocational training;
+- Employment and workers management;
+- Exploitation of the vulnerabilities of persons resulting in harmful behavior;
+- General purpose social scoring;
+- Law enforcement;
+- Management and operation of critical infrastructure;
+- Migration, asylum and border control management;
+- Predictive policing;
+- Real-time remote biometric identification in public spaces;
+- Recommender systems of social media platforms;
+- Scraping of facial images (from the internet or otherwise); and/or
+- Subliminal manipulation