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

Mistral AI's first open source dense model released September 2023. Mistral-7B-Instruct-v0.3 Large Language Model (LLM) is an instruct fine‑tuned version of the Mistral‑7B‑v0.3. It has an extended vocabulary and supports the v3 Tokenizer, enhancing language understanding and generation. Additionally function calling is enabled.

This is based on the implementation of Mistral-7B-Instruct-v0.3 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 Mistral 7B Instruct v0.3 on-device

Please follow the LLM on-device deployment tutorial.

Getting Started

Download pre-exported model assets from Mistral-7B-Instruct-v0.3 on Qualcomm® AI Hub.

Model Details

Model Type: Model_use_case.text_generation

Model Stats:

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

Performance Summary

Model	Runtime	Precision	Chipset	Context Length	Response Rate (tokens per second)	Time To First Token (range, seconds)
Mistral-7B-Instruct-v0.3	QNN_CONTEXT_BINARY	w4a16	Snapdragon® 8 Elite Mobile	4096	12.56	0.16565000000000002 - 5.300800000000001

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

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