Comprehension of trade term sheets and confirmations
Project description
Confirms Package
Overview
THIS PACKAGE CONTAINS RESEARCH CODE AND IS NOT INTENDED FOR PRODUCTION USE
This package contains research code that can perform AI comprehension of trade confirmations, model source code, and model documentation for the purposes of model governance.
The objective is to support the following use cases:
- Validation of trade capture using LLM comprehension of trade confirmations
- Validation of model documentation using LLM comprehension of source code
- Validation of source code, identifying bugs and deviations from the approved methodology
- LLM generation of model documentation and release note drafts
Installation on GPU
- Set environment variables FORCE_CMAKE=1;CMAKE_ARGS=-DLLAMA_CUBLAS=on
- Note: In PyCharm, use Settings > Tools > Terminal > Environment variables
- Run 'pip install --upgrade --force-reinstall llama-cpp-python --no-cache-dir'
- After this run 'pip install -r requirements.txt'
Copyright
Each individual contributor holds copyright over their contributions to the project. The project versioning is the sole means of recording all such contributions and copyright details. Specifying corporate affiliation or work email along with the commit shall have no bearing on copyright ownership and does not constitute copyright assignment to the employer. Submitting a contribution to this project constitutes your acceptance of these terms.
Because individual contributions are often changes to the existing code, copyright notices in project files must specify The Project Contributors and never an individual copyright holder.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
Built Distribution
File details
Details for the file confirms-0.2.0-py3-none-any.whl
.
File metadata
- Download URL: confirms-0.2.0-py3-none-any.whl
- Upload date:
- Size: 8.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.10.11
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | e0a673de1763f4a9dfe8927161ee4ae8057339d435ccc6fdc4cdd023ee46b6ba |
|
MD5 | d2c757f9703f322f3c65723edf704739 |
|
BLAKE2b-256 | ec3d7fe3e8eba24b622f14defb190f53506a934c589ebdd39a549f85c8e9befe |