Baichuan-7B: Optimized for Mobile Deployment

Large language model achieving state-of-the-art performance on Chinese and English language benchmarks

Baichuan-7B is a family of LLMs. It achieves the state-of-the-art performance of its size on standard Chinese and English authoritative benchmarks (C-EVAL/MMLU). 4-bit weights and 16-bit activations making it suitable for on-device The model is quantized to deployment. For Prompt and output length specified below, the time to first token is Llama-PromptProcessor-Quantized's latency and average time per addition token is Llama-TokenGenerator-KVCache-Quantized's latency.

This is based on the implementation of Baichuan-7B found here. More details on model performance accross various devices, can be found here.

Model Details

• Model Type: Text generation
• Model Stats:
  • Number of parameters: 7B
  • Model size: 3.9GB
  • Model-1 (Prompt Processor): Baichuan-PromptProcessor-Quantized
  • Max context length: 1024
  • Prompt processor input: 1024 tokens
  • Prompt processor output: 1024 output tokens + KVCache for token generator
  • Model-2 (Token Generator): Baichuan-TokenGenerator-KVCache-Quantized
  • Token generator input: 1 input token + past KVCache
  • Token generator output: 1 output token + KVCache for next iteration
  • Decoding length: 1024 (1 output token + 1023 from KVCache)
  • Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.

Device	Chipset	Target Runtime	Inference Time (ms)	Peak Memory Range (MB)	Precision	Primary Compute Unit	Target Model
Samsung Galaxy S23 Ultra (Android 13)	Snapdragon® 8 Gen 2	QNN Model Library	108.059 ms	1 - 107 MB	UINT16	NPU	Baichuan-TokenGenerator-KVCache-Quantized
Samsung Galaxy S23 Ultra (Android 13)	Snapdragon® 8 Gen 2	QNN Model Library	2599.326 ms	0 - 38 MB	UINT16	NPU	Baichuan-PromptProcessor-Quantized

License

• The license for the original implementation of Baichuan-7B can be found here.

References

• Baichuan 2: Open Large-scale Language Models
• Source Model Implementation

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