v0.46.1

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

README.md

@@ -11,61 +11,58 @@ pipeline_tag: text-generation
 
 ![](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/qwen2_7b_instruct/web-assets/model_demo.png)
 
-# Qwen2-7B-Instruct: Optimized for Mobile Deployment
-## State-of-the-art large language model useful on a variety of language understanding and generation tasks
-
+# Qwen2-7B-Instruct: Optimized for Qualcomm Devices
 
 The Qwen2-7B-Instruct is a state-of-the-art multilingual language model with 7.07 billion parameters, excelling in language understanding, generation, coding, and mathematics.
 
-This model is an implementation of Qwen2-7B-Instruct found [here](https://github.com/QwenLM/Qwen2.5).
-
+This is based on the implementation of Qwen2-7B-Instruct found [here](https://github.com/QwenLM/Qwen2.5).
+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/qwen2_7b_instruct) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).
 
- More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/qwen2_7b_instruct).
+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 Qwen2-7B-Instruct on-device
 
+Please follow the [LLM on-device deployment](https://github.com/quic/ai-hub-apps/tree/main/tutorials/llm_on_genie) tutorial.
 
-### Model Details
+## Getting Started
+Download pre-exported model assets from **[Qwen2-7B-Instruct on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/qwen2_7b_instruct)**.
 
-- **Model Type:** Model_use_case.text_generation
-- **Model Stats:**
-  - Input sequence length for Prompt Processor: 128
-  - Context length: 4096
-  - Number of parameters: 7.07B
-  - Precision: w4a16 + w8a16 (few layers)
-  - Information about the model parts: Prompt Processor and Token Generator are split into 5 parts each. Each corresponding Prompt Processor and Token Generator part share weights.
-  - Supported languages: English, Chinese, German, French, Spanish, Portuguese, Italian, Dutch, Russian, Czech, Polish, Arabic, Persian, Hebrew, Turkish, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Lao, Burmese, Cebuano, Khmer, Tagalog, Hindi, Bengali, Urdu.
-  - 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)
-|---|---|---|---|---|---|
-| Qwen2-7B-Instruct | w4a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_CONTEXT_BINARY | 13.65 | 0.170593 - 5.458976 | -- | Use Export Script |
 
-## Deploying Qwen2-7B-Instruct on-device
+## Model Details
 
-Please follow the [LLM on-device deployment](https://github.com/quic/ai-hub-apps/tree/main/tutorials/llm_on_genie) tutorial.
+**Model Type:** Model_use_case.text_generation
 
+**Model Stats:**
+- Input sequence length for Prompt Processor: 128
+- Context length: 4096
+- Number of parameters: 7.07B
+- Precision: w4a16 + w8a16 (few layers)
+- Information about the model parts: Prompt Processor and Token Generator are split into 5 parts each. Each corresponding Prompt Processor and Token Generator part share weights.
+- Supported languages: English, Chinese, German, French, Spanish, Portuguese, Italian, Dutch, Russian, Czech, Polish, Arabic, Persian, Hebrew, Turkish, Japanese, Korean, Vietnamese, Thai, Indonesian, Malay, Lao, Burmese, Cebuano, Khmer, Tagalog, Hindi, Bengali, Urdu.
+- 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)
+|---|---|---|---|---|---|---
+| Qwen2-7B-Instruct | QNN_CONTEXT_BINARY | w4a16 | Snapdragon® 8 Elite Mobile | 4096 | 13.65 | 0.170593 - 5.458976
 
 ## License
 * The license for the original implementation of Qwen2-7B-Instruct can be found
   [here](https://huggingface.co/Qwen/Qwen2-7B-Instruct/blob/main/LICENSE).
 
-
-
 ## References
 * [Qwen2 Technical Report](https://arxiv.org/abs/2407.10671v1)
 * [Source Model Implementation](https://github.com/QwenLM/Qwen2.5)
 
-
-
 ## 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;