Hugging Face's logo

qualcomm
/
IBM-Granite-3B-Code-Instruct

Text Generation
PyTorch
llm
generative_ai
android
Model card Files Community
IBM-Granite-3B-Code-Instruct / README.md
shreyajn's picture
shreyajn
Upload README.md with huggingface_hub
b2d4b1c verified
preview code
|
raw
history blame
4.91 kB
metadata
library_name: pytorch
license: apache-2.0
pipeline_tag: text-generation
tags:
  - llm
  - generative_ai
  - android

IBM-Granite-3B-Code-Instruct: Optimized for Mobile Deployment

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

Granite-3B-Code-Instruct-2K is a 3B parameter model fine tuned from Granite-3B-Code-Base-2K on a combination of permissively licensed instruction data to enhance instruction following capabilities including logical reasoning and problem-solving skills.

This model is an implementation of IBM-Granite-3B-Code-Instruct found here.

More details on model performance accross various devices, can be found here.

Model Details

  • Model Type: Text generation
  • Model Stats:
    • Input sequence length for Prompt Processor: 128
    • Context length: 2048
    • Number of parameters: 3.48B
    • Precision: fp16
    • Num of key-value heads: 32
    • 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: 7 GB
    • Prompt processor input (part1): 128 tokens
    • Prompt processor output (part1): Embeddings output
    • Prompt processor input (other parts): 128 tokens + KVCache initialized with pad token
    • Prompt processor output (other parts): 128 output tokens + KVCache for token generator
    • Token generator model size: 7 GB
    • Token generator input (part1): 1 token
    • Token generator output (part1): Embeddings output
    • Token generator input (other parts): 1 input token + past KVCache
    • Token generator output (other parts): 1 output token + KVCache for next iteration
    • Use: Initiate conversation with prompt-processor and then token generator for subsequent iterations.
    • Supported natural languages: English
    • Supported programming languages: The Granite code foundation models support 116 programming languages including Python, Javascript, Java, C++, Go, and Rust.
    • Minimum QNN SDK version required: 2.27.7
    • 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 (2048 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)
IBM-Granite-3B-Code Samsung Galaxy S24 Snapdragon® 8 Gen 3 QNN 5.47 0.3262 - 5.2192

License

  • The license for the original implementation of IBM-Granite-3B-Code-Instruct can be found here.
  • The license for the compiled assets for on-device deployment can be found here

References

Community

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