|
|
--- |
|
|
library_name: pytorch |
|
|
license: other |
|
|
tags: |
|
|
- llm |
|
|
- generative_ai |
|
|
- android |
|
|
pipeline_tag: text-generation |
|
|
|
|
|
--- |
|
|
|
|
|
 |
|
|
|
|
|
# Allam-7B: Optimized for Mobile Deployment |
|
|
## Large Language Model supporting arabic and english |
|
|
|
|
|
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](https://aihub.qualcomm.com/models/allam_7b). |
|
|
|
|
|
### Model Details |
|
|
|
|
|
- **Model Type:** Model_use_case.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 | Precision | Device | Chipset | Target Runtime | Response Rate (tokens per second) | Time To First Token (range, seconds) |
|
|
|---|---|---|---|---|---| |
|
|
| ALLaM-7B-Quantized | w4a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 9.5 | 0.23854499999999998 - 1.399168 | -- | -- | |
|
|
|
|
|
## Deploy Allam 7B on Snapdragon X Elite NPU |
|
|
|
|
|
Please follow the [LLM on-device deployment](https://github.com/quic/ai-hub-apps/tree/main/tutorials/llm_on_genie) tutorial. |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
## 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:[email protected]). |
|
|
|
|
|
## 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 |
|
|
|
