v0.30.5

See https://github.com/quic/ai-hub-models/releases/v0.30.5 for changelog.

README.md

@@ -0,0 +1,98 @@
+---
+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/qwen2_5_7b_instruct/web-assets/model_demo.png)
+
+# Qwen2.5-7B-Instruct: Optimized for Mobile Deployment
+## State-of-the-art large language model useful on a variety of language understanding and generation tasks
+
+
+The Qwen2.5-7B-Instruct is a state-of-the-art multilingual language model with 7 billion parameters, excelling in language understanding, generation, coding, and mathematics. AI Hub provides with four QNN context binaries (shared weights) that can be deployed on Snapdragon 8 Elite with Genie SDK.
+
+This model is an implementation of Qwen2.5-7B-Instruct found [here](https://github.com/QwenLM/Qwen2.5).
+
+
+ More details on model performance across various devices, can be found [here](https://aihub.qualcomm.com/models/qwen2_5_7b_instruct).
+
+### Model Details
+
+- **Model Type:** Model_use_case.text_generation
+- **Model Stats:**
+  - Input sequence length for Prompt Processor: 128
+  - Context length: 4096
+  - Number of parameters: 7B
+  - Precision: w4a16 + w8a16 (few layers)
+  - Num of key-value heads: 4
+  - Information about the model parts: Prompt Processor and Token Generator are split into 6 parts each. Each corresponding Prompt Processor and Token Generator part share weights.
+  - Prompt processor model size: 4.61 GB
+  - Prompt processor input (part1): 128 tokens
+  - Prompt processor output (part1): Embeddings output
+  - Prompt processor input (other parts): 128 tokens + KVCache initialized with pad token
+  - Prompt processor output (other parts): 128 output tokens + KVCache for token generator
+  - Token generator model size: 4.61 GB
+  - Token generator input (part1): 128 tokens
+  - Token generator output (part1): Embeddings output
+  - Token generator input (other parts): 1 input token + past KVCache
+  - Token generator output (other parts): 1 output token + KVCache for next iteration
+  - Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
+  - Minimum QNN SDK version required: 2.27.7
+  - Supported languages: Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.
+  - 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)
+|---|---|---|---|---|---|
+| Qwen2.5-3B-Instruct | w4a16 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN | 15.40274 | 0.1356538 - 4.3409216 | -- | Use Export Script |
+| Qwen2.5-3B-Instruct | w4a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 12.33811 | 0.1749494 - 5.5983808 | -- | Use Export Script |
+
+## Deploying Qwen2.5-7B-Instruct on-device
+
+Please follow the [LLM on-device deployment](https://github.com/quic/ai-hub-apps/tree/main/tutorials/llm_on_genie) tutorial.
+
+
+
+## License
+* The license for the original implementation of Qwen2.5-7B-Instruct can be found
+  [here](https://huggingface.co/Qwen/Qwen2.5-7B/blob/main/LICENSE).
+* 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
+* [Qwen2.5 Technical Report](https://arxiv.org/abs/2412.15115)
+* [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.
+* 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:
+
+- 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