v0.46.1

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

README.md

@@ -11,35 +11,14 @@ pipeline_tag: text-generation
 
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/llama_v2_7b_chat/web-assets/model_demo.png)
 
-# Llama-v2-7B-Chat: Optimized for Mobile Deployment
-## State-of-the-art large language model useful on a variety of language understanding and generation tasks
-
+# Llama-v2-7B-Chat: Optimized for Qualcomm Devices
 
 Llama 2 is a family of LLMs. The "Chat" at the end indicates that the model is optimized for chatbot-like dialogue. 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. For Prompt and output length specified below, the time to first token is Llama-PromptProcessor-Quantized's latency and average time per addition token is Llama-TokenGenerator-KVCache-Quantized's latency.
 
-This model is an implementation of Llama-v2-7B-Chat found [here](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf).
-
-
- More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/llama_v2_7b_chat).
-
-**WARNING**: The model assets are not readily available for download due to licensing restrictions.
+This is based on the implementation of Llama-v2-7B-Chat found [here](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf).
+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_v2_7b_chat) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
-### Model Details
-
-- **Model Type:** Model_use_case.text_generation
-- **Model Stats:**
-  - Input sequence length for Prompt Processor: 1024
-  - Context length: 1024
-  - Precision: w4a16 + w8a16 (few layers)
-  - 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. For Llama-v2-7B-Chat, both values in the range are the same since prompt length is the full context length (1024 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-v2-7B-Chat | w4a16 | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_CONTEXT_BINARY | 12.85 | 1.49583 - 1.49583 | -- | -- |
-| Llama-v2-7B-Chat | w4a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_CONTEXT_BINARY | 11.2 | 1.919 - 1.919 | -- | -- |
-| Llama-v2-7B-Chat | w4a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 17.94 | 1.44 - 1.44 | -- | -- |
+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 2 on-device
 
@@ -77,27 +56,50 @@ You can test the function by calling it with different values of `n`, like this:
 print(fibonacci(5))
 ~~~
 
+## 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_v2_7b_chat) 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-v2-7B-Chat on GitHub](https://github.com/quic/ai-hub-models/blob/main/qai_hub_models/models/llama_v2_7b_chat) for usage instructions.
+
 
+## Model Details
+
+**Model Type:** Model_use_case.text_generation
+
+**Model Stats:**
+- Input sequence length for Prompt Processor: 1024
+- Context length: 1024
+- Precision: w4a16 + w8a16 (few layers)
+- 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. For Llama-v2-7B-Chat, both values in the range are the same since prompt length is the full context length (1024 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-v2-7B-Chat | QNN_CONTEXT_BINARY | w4a16 | Snapdragon® 8 Elite Mobile | 1024 | 17.94 | 1.44 - 1.44
+| Llama-v2-7B-Chat | QNN_CONTEXT_BINARY | w4a16 | Snapdragon® X Elite | 1024 | 11.2 | 1.919 - 1.919
+| Llama-v2-7B-Chat | QNN_CONTEXT_BINARY | w4a16 | Snapdragon® 8 Gen 3 Mobile | 1024 | 12.85 | 1.49583 - 1.49583
 
 ## License
 * The license for the original implementation of Llama-v2-7B-Chat can be found
   [here](https://github.com/facebookresearch/llama/blob/main/LICENSE).
 
-
-
 ## References
 * [LLaMA: Open and Efficient Foundation Language Models](https://arxiv.org/abs/2302.13971)
 * [Source Model Implementation](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf)
 
-
-
 ## Community
-* Join [our AI Hub Slack community](https://qualcomm-ai-hub.slack.com/join/shared_invite/zt-2d5zsmas3-Sj0Q9TzslueCjS31eXG2UA#/shared-invite/email) to collaborate, post questions and learn more about on-device AI.
+* 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
 
-Model may not be used for or in connection with any of the following applications:
+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;