An experiment to log LLM logs using opentelemetry platforms

Some finetuning experiments, from SLM(1-3B LLMs) to larger LLMs. The focus of these finetunes is to build better eval models.

LMQL implementation of Tree of thought

Chain of Verification implementation in Langchain

Pgit is a prompt control system and validator for LLM prompts.

Monitoring LLMs made easy

extraction the most important information from resumes.

An LLM tool for VCs, solving all the issues for top of the funnel for firms.

An attempt to fine-tune GPT-3.5 via uploading your PDF and csv files.

A fine-tuning library leveraging distilled GPT-4 outputs to fine-tune to GPT-3.5 for better accuracy.

ORB/DAISY based feature extractor predicting left/right turn probability of a vehicle.

POCs around embedchain for QA around PDF/text files

LLM agents to derive market research insights from qualitative and quantitative data.

langchain+webscraping for downstream tasks.

Some LLM experiments like codegen, QA and more

Solutions to https://hackattic.com/challenges to build better engineering muscle.

Chainlit chat for Falcon LLMs