TeleChat2-3B: Optimized for Qualcomm Devices

For more details, including benchmark evaluation, hardware requirements, and inference performance, please refer to https://github.com/Tele-AI/TeleChat2

This is based on the implementation of TeleChat2-3B 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 TeleChat2-3B on-device

Please follow the LLM on-device deployment tutorial.

Getting Started

Below are pre-exported model assets ready for deployment.

For more device-specific assets and performance metrics, visit TeleChat2-3B on Qualcomm® AI Hub.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

• Information about the model parts: Prompt Processor and Token Generator are split into 7 parts each. Each corresponding Prompt Processor and Token Generator part share weights.
• Input sequence length for Prompt Processor: 128
• Maximum context length: 4096
• Minimum QNN SDK version required: 2.45
• Num of key-value heads: 8 for KV, 16 for Q
• Precision: w8, w8a16 is supported
• Prompt processor input (other parts): 128 tokens + KVCache initialized with pad token
• Prompt processor input (part1): 128 tokens
• Prompt processor output (other parts): 128 output tokens + KVCache for token generator
• Prompt processor output (part1): Embeddings output
• Response Rate: Rate of response generation after the first response token.
• 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).
• Token generator input (other parts): 1 input token + past KVCache
• Token generator input (part1): 128 tokens
• Token generator output (other parts): 1 output token + KVCache for next iteration
• Token generator output (part1): Embeddings output
• Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.

Performance Summary

License

• The license for the original implementation of TeleChat2-3B can be found here.

References

• Technical Report of TeleChat2, TeleChat2.5 and T1
• Source Model Implementation

Community

• For questions or feedback, chat with our engineers in Qualcomm® AI Hub Workbench.

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