Mistral-7B-Instruct-v0.3: Optimized for Qualcomm Devices

Getting Started

Getting Started

Model Details

• Context length: 4096
• Information about the model parts: Prompt Processor and Token Generator are split into 4 parts each. Each corresponding Prompt Processor and Token Generator part share weights.
• Input sequence length for Prompt Processor: 128
• Minimum QNN SDK version required: 2.27.7
• Num of key-value heads: 8
• Number of parameters: 7.3B
• Precision: w4a16 + w8a16 (few layers)
• Prompt processor input: 128 tokens + KVCache initialized with pad token
• Prompt processor model size: 4.17 GB
• Prompt processor output: 128 output tokens + KVCache for token generator
• Response Rate: Rate of response generation after the first response token.
• Supported languages: English.
• 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: 1 input token + past KVCache
• Token generator model size: 4.17 GB
• Token generator output: 1 output token + KVCache for next iteration
• Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.

Performance Summary

License

• The license for the original implementation of Mistral-7B-Instruct-v0.3 can be found here.

References

• Mistral 7B
• 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

• 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