Llama3-TAIDE-LX-8B-Chat-Alpha1: Optimized for Mobile Deployment

State-of-the-art large language model useful on a variety of language understanding and generation tasks

The Llama3-TAIDE-LX-8B-Chat-Alpha1 LLM model is based on Meta's released LLaMA3-8b model, fine-tuned on Traditional Chinese data, and enhanced for office tasks and multi-turn dialogue capabilities through instruction tuning. The TAIDE model is incorporating text and training materials from various fields in Taiwan to enhance the model's ability to respond in Traditional Chinese and perform specific tasks such as automatic summarization, writing emails, articles, and translating between Chinese and English.

This model is an implementation of Llama3-TAIDE-LX-8B-Chat-Alpha1 found here.

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
  • Context length: 4096
  • Number of parameters: 8B
  • Model size: 4.8GB
  • Precision: w4a16 + w8a16 (few layers)
  • Num of key-value heads: 8
  • Model-1 (Prompt Processor): Llama-PromptProcessor-Quantized
  • Prompt processor input: 128 tokens + position embeddings + attention mask + KV cache inputs
  • Prompt processor output: 128 output tokens + KV cache outputs
  • Model-2 (Token Generator): Llama-TokenGenerator-Quantized
  • Token generator input: 1 input token + position embeddings + attention mask + KV cache inputs
  • Token generator output: 1 output token + KV cache outputs
  • Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
  • Minimum QNN SDK version required: 2.27.7
  • Supported languages: English, Traditional Chinese
  • 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)
Llama3-TAIDE-LX-8B-Chat-Alpha1	Snapdragon 8 Elite QRD	Snapdragon® 8 Elite	QNN	12.9262	0.159383 - 5.100256
Llama3-TAIDE-LX-8B-Chat-Alpha1	Snapdragon X Elite CRD	Snapdragon® X Elite	QNN	10.0367	0.211644 - 6.772608

Deploying Llama-3-TAIDE on-device

Please follow the LLM on-device deployment tutorial.

License

• The license for the original implementation of Llama3-TAIDE-LX-8B-Chat-Alpha1 can be found here.
• The license for the compiled assets for on-device deployment can be found here

References

• LLaMA: Open and Efficient Foundation 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