trex
autolabel
| trex | autolabel | |
|---|---|---|
| 3 | 10 | |
| 238 | 1,788 | |
| 0.4% | 2.4% | |
| 6.6 | 9.4 | |
| 8 months ago | 10 days ago | |
| Python | Python | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
trex
-
Show HN: Generate JSON mock data for testing/initial app development
A friend of mine built a tool called Trex that you might find helpful, check it out here: https://github.com/automorphic-ai/trex
It's very consistent at generating templated data.
- Intelligently transform unstructured to structured output (JSON, Regex, CFG)
autolabel
-
NLP Research in the Era of LLMs
Try this: https://github.com/refuel-ai/autolabel
Then the main challenge just becomes prompt design, which can sometimes be nebulous for NLP annotation.
-
[P] Autolabel: data labeling with LLMs
Wanted to share an open source project we've been working on for the last few weeks: Autolabel is an open source Python library to label and enrich text datasets with LLMs (Large Language Models).
- Label clean and enrich text datasets with LLMs
-
Show HN: Autolabel, a Python library to label and enrich text data with LLMs
Yep! I totally understand the concerns around not being able to share data externally - the library currently supports open source, self-hosted LLMs through huggingface pipelines (https://github.com/refuel-ai/autolabel/blob/main/src/autolab...), and we plan to add more support here for models like llama cpp that can be run without many constrains on hardware
-
21-Jun-2023
Label, clean and enrich text datasets with Large Language Models (https://github.com/refuel-ai/autolabel)
- Show HN: Autolabel a Python library to label and enrich text data with LLMs
-
LLMs can label data as well as human annotators, but 20 times faster
>> don't trust that there was no funny business going on in generating the results for this blog
All the datasets and labeling configs used for these experiments are available in our Github repo (https://github.com/refuel-ai/autolabel) as mentioned in the report. Hope these are useful!
What are some alternatives?
PentestGPT - A GPT-empowered penetration testing tool
ChainFury - π¦ Production grade chaining engine behind TuneChat. Self host today!
graph-of-thoughts - Official Implementation of "Graph of Thoughts: Solving Elaborate Problems with Large Language Models"
zamm - Experimental AI chat app
sycamore - π Sycamore is an LLM-powered search and analytics platform for unstructured data.
lanarky - The web framework for building LLM microservices
ChatGLM2-6B - ChatGLM2-6B: An Open Bilingual Chat LLM | εΌζΊεθ―ε―Ήθ―θ―θ¨ζ¨‘ε
llm-gateway - Gateway for secure & reliable communications with OpenAI and other LLM providers
JSON-Schema Faker - JSON-Schema + fake data generators
GeniA - Your Engineering Gen AI Team member π§¬π€π»
safe-rlhf - Safe RLHF: Constrained Value Alignment via Safe Reinforcement Learning from Human Feedback
delta-buddy - Introducing Delta-Buddy: Your ultimate Delta Lake companion! π Streamline your data journey with an AI-powered chatbot. Ask Delta-Buddy anything about your Delta Lake.