horus-ai-labs/DistillFlow
Library for model distillation
This toolkit helps machine learning engineers and researchers make large language models (LLMs) more efficient and cost-effective. It takes a powerful, but resource-intensive, LLM and a smaller, less capable LLM, along with a dataset, to produce a compact, specialized LLM that performs almost as well but uses fewer computing resources. This is ideal for deploying LLMs in production environments where speed and cost are critical.
165 stars. No commits in the last 6 months.
Use this if you need to deploy a smaller, faster, and more affordable version of a large language model for practical applications like chatbots, content generation, or specialized text analysis.
Not ideal if you primarily need to train brand-new LLMs from scratch or are only looking to fine-tune an existing model without reducing its size and complexity.
Stars
165
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Sep 06, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/horus-ai-labs/DistillFlow"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
scaleapi/llm-engine
Scale LLM Engine public repository
AGI-Arena/MARS
The official implementation of MARS: Unleashing the Power of Variance Reduction for Training Large Models
modelscope/easydistill
a toolkit on knowledge distillation for large language models
AGI-Edgerunners/LLM-Adapters
Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient...
Wang-ML-Lab/bayesian-peft
Bayesian Low-Rank Adaptation of LLMs: BLoB [NeurIPS 2024] and TFB [NeurIPS 2025]