Allam-7B: Optimized for Mobile Deployment
Llama2 based large language model supporting English and Arabic
Allam 7B is SDAIA's first generation edge model, optimized for performance on Snapdragon X Elite.
More details on model performance across various devices, can be found here.
Model Details
- Model Type: Text generation
- Model Stats:
- Input sequence length for Prompt Processor: 128
- Max context length: 1024
- Num of key-value heads: 32
- Number of parameters: 7B
- Precision: w4a16 + w8a16 (few layers)
- Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
- Minimum QNN SDK version required: 2.28.2
- Supported languages: English, Arabic.
- 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 | Device | Chipset | Target Runtime | Response Rate (tokens per second) | Time To First Token (range, seconds) |
---|---|---|---|---|---|
ALLaM-7B-Quantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 21.05 | 0.092289 - 2.9532736 |
Deploy Allam 7B on Snapdragon X Elite NPU
Please follow the LLM on-device deployment tutorial.
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
Inference API (serverless) does not yet support pytorch models for this pipeline type.