You can deploy this model and start earning money today!

qualcomm/
Llama3-TAIDE-LX-8B-Chat-Alpha1

Name: Llama3-TAIDE-LX-8B-Chat-Alpha1
Availability: InStock

Views

No views yet

Llama3-TAIDE-LX-8B-Chat-Alpha1: Optimized for Qualcomm Devices

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 is based on the implementation of Llama3-TAIDE-LX-8B-Chat-Alpha1 found here. This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the Qualcomm® AI Hub Models library to export with custom configurations. More details on model performance across various devices, can be found here.

Qualcomm AI Hub Models uses Qualcomm AI Hub Workbench to compile, profile, and evaluate this model. Sign up to run these models on a hosted Qualcomm® device.

Deploying Llama3-TAIDE-LX-8B-Chat-Alpha1 on-device

Follow the GenieX quickstart to install GenieX and deploy the model on a target device.

You'll need to export the model artifact using the steps below, then follow Run a Local Model with GenieX.

See the LLM-on-Genie tutorial to run with the Genie runtime. Note: Genie support will be deprecated soon.

Getting Started

Due to licensing restrictions, we cannot distribute pre-exported model assets for this model. Use the Qualcomm® AI Hub Models Python library to compile and export the model with your own:

Custom weights (e.g., fine-tuned checkpoints)
Custom input shapes
Target device and runtime configurations

See our repository for Llama3-TAIDE-LX-8B-Chat-Alpha1 on GitHub for usage instructions.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

Response Rate: Rate of response generation after the first response token.
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).

Performance Summary

Model	Runtime	Precision	Chipset	Context Length	Response Rate (tokens per second)	Time To First Token (range, seconds)
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIE	w4a16	Snapdragon® 8 Elite Gen 5 Mobile	4096	16.677952766418457	0.09902849999999999 - 3.1689119999999997
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIE	w4a16	Snapdragon® 8 Elite Mobile	4096	15.232870101928711	0.12542460000000002 - 4.013587200000001
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIE	w4a16	Snapdragon® X2 Elite	4096	22.244472312927247	0.1362849 - 4.3611168
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIE	w4a16	Snapdragon® X Elite	4096	7.201948595046997	0.22299370000000002 - 7.1357984000000005
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIE	w4a16	Qualcomm® Dragonwing™ IQ-9075	4096	11.305743980407716	0.1831854 - 5.8619328
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIE	w4a16	Qualcomm® Dragonwing™ IQ-X7181	4096	7.201948595046997	0.22299370000000002 - 7.1357984000000005
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIE	w4a16	Qualcomm® Dragonwing™ Q-8750	4096	15.232870101928711	0.12542460000000002 - 4.013587200000001
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Snapdragon® 8 Elite Gen 5 Mobile	4096	15.882413	0.1269 - 4.0608
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Snapdragon® 8 Elite Mobile	4096	14.387173	0.136 - 4.352
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Snapdragon® X2 Elite	4096	22.931794	0.0978 - 3.1296
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Snapdragon® X Elite	4096	11.604306	0.21669999999999998 - 6.934399999999999
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-8275	4096	9.681806	0.214178 - 6.853696
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-9075	4096	10.311971	0.2072 - 6.6304
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ IQ-X7181	4096	11.604306	0.21669999999999998 - 6.934399999999999
Llama3-TAIDE-LX-8B-Chat-Alpha1	GENIEX_QAIRT	w4a16	Qualcomm® Dragonwing™ Q-8750	4096	14.387173	0.136 - 4.352

License

The license for the original implementation of Llama3-TAIDE-LX-8B-Chat-Alpha1 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

This 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

qualcomm/Llama3-TAIDE-LX-8B-Chat-Alpha1