-
uptrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
We are working on an open-source project, BlindAI (https://github.com/mithril-security/blindai) to answer exactly that: privacy when sending data to remote AI models.
I am building an open source project which helps in collecting the high quality retraining dataset for fine-tuning LLMs. Check out https://github.com/uptrain-ai/uptrain
Hey Taenk, Arnaudvl makes a good point that the T5 is not really trained to be a chatbot. I forgot to mention the flan-alpaca model from declare-labs (it's super recent). They took the Flan-T5 and trained it on the Alpaca dataset. I'm using it right now for a project as a chatbot and getting good results. Here's an example payload I've used to get a good response:
Related posts
-
[P] Secret Whisper: Deploy OpenAI Whisper model with privacy using BlindAI
-
[P] Introducing BlindAI, an Open-source, fast and privacy-friendly AI deployment solution. Benefit from state-of-the-art AI without ever revealing your data!
-
Integrating Spade: Synthesizing Assertions for LLMs into My OSS Project
-
Sharing learnings from evaluating Million+ LLM responses
-
Show HN: UpTrain (YC W23) – open-source tool to evaluate LLM response quality