Qwen2.5-1.5B-Instruct: Optimized for Mobile Deployment
State-of-the-art large language model useful on a variety of language understanding and generation tasks
The Qwen2.5-1.5B-Instruct is a state-of-the-art multilingual language model with 1.5 billion parameters, excelling in language understanding, generation, coding, and mathematics.
This model is an implementation of Qwen2.5-1.5B-Instruct found here.
More details on model performance across various devices, can be found here.
Model Details
- Model Type: Model_use_case.text_generation
- Model Stats:
- Input sequence length for Prompt Processor: 128
- Context length: 4096
- Precision: w4 + w8 (few layers) with fp16 activations
- 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 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 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) |---|---|---|---|---|---| | Qwen2.5-1.5B-Instruct | w4 | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | GENIE | 23.48920135498047 | 0.09537269999999999 - 3.0519263999999997 | -- | Use Export Script | | Qwen2.5-1.5B-Instruct | w4 | Snapdragon X Elite CRD | Snapdragon® X Elite | GENIE | 12.98912 | 0.16027780000000003 - 5.128889600000001 | -- | Use Export Script |
Deploying Qwen2.5-1.5B-Instruct on-device
Please follow the LLM on-device deployment tutorial.
License
- The license for the original implementation of Qwen2.5-1.5B-Instruct can be found here.
- The license for the compiled assets for on-device deployment can be found here
References
Community
- Join our AI Hub Slack community to collaborate, post questions and learn more about on-device AI.
- For questions or feedback please reach out to us.
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