MFTCoder
Task-based fine-tuner
A framework for fine-tuning large language models with multiple tasks to improve their accuracy and efficiency
High Accuracy and efficiency multi-task fine-tuning framework for Code LLMs. This work has been accepted by KDD 2024.
637 stars
7 watching
67 forks
Language: Python
last commit: 9 days ago
Linked from 1 awesome list
customizablemulti-model-supportmulti-task-fine-tuningmulti-task-learninguser-friendly
ethicalml/awesome-production-machine-learningRelated projects:
| Repository | Description | Stars |
|---|---|---|
| codefuse-ai/codefuse-devops-eval | An evaluation suite for assessing foundation models in the DevOps field. | 685 |
 n-waves/multifit | Reproduces results from a paper on efficient multi-lingual language model fine-tuning using a rewritten framework on top of the fastai library | 284 |
| codefuse-ai/test-agent | A tool that empowers software testing with large language models. | 559 |
 roboflow/maestro | A tool to streamline fine-tuning of multimodal models for vision-language tasks | 1,392 |
 fff-rs/juice | A machine learning framework designed to be extensible and agnostic, with support for multiple backends and linear algebra libraries. | 1,111 |
| codefuse-ai/codefuse-chatbot | An AI-powered tool designed to simplify and optimize various stages of the software development lifecycle | 1,181 |
 salesforce/codetf | A comprehensive library for transformer-based code language models and code intelligence tasks. | 1,458 |
| codefuse-ai/codefuse-devops-model | An industrial-first language model for answering questions in the DevOps domain | 588 |
 google-research/flan | A repository providing tools and datasets to fine-tune language models for specific tasks | 1,474 |
 jerry1993-tech/cornucopia-llama-fin-chinese | A Chinese finance-focused large language model fine-tuning framework | 589 |
 bfrymire/crispy | A unit testing framework built in Game Maker Language for GameMaker Studio 2+, allowing developers to write and run tests within their projects. | 39 |
 johnathan79717/codeforces-parser | Generates sample tests and input/output files for competitive programming contests | 137 |
 asappresearch/flambe | An ML framework for accelerating research and its integration into production workflows | 262 |
 cuis15/fcfl | An implementation of Fair and Consistent Federated Learning using Python. | 20 |
 andreafioraldi/motherfucking-ctf | A CTF platform with customizable challenges and scoring | 49 |