hao-ai-lab/Consistency_LLM

[ICML 2024] CLLMs: Consistency Large Language Models

38
/ 100
Emerging

This project offers a way to make large language models (LLMs) generate text, code, or answers much faster. It takes an existing LLM, along with a dataset you've used to train it, and outputs a specialized version of that LLM that can produce results several times quicker. This is ideal for developers or researchers who build and deploy LLMs for applications like chatbots, code generation tools, or problem-solving assistants.

413 stars. No commits in the last 6 months.

Use this if you are a developer or researcher looking to significantly speed up the inference (response time) of your existing large language models without complex architectural changes or needing a 'draft' model.

Not ideal if you are looking for a pre-built, end-user application or if you do not have the technical expertise to work with and train large language models.

LLM deployment text generation code generation AI inference optimization natural language processing
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

413

Forks

22

Language

Python

License

Apache-2.0

Last pushed

Nov 16, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/hao-ai-lab/Consistency_LLM"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.