Pinned Repositories
docling
Get your documents ready for gen AI
argilla
✨Argilla: the open-source feedback platform for LLMs
captions
transcripts and captions for 3blue1brown videos
deep_nlp_on_sf_literature
Multi-pronged, multi-stage analysis of a 3.5M-sentences science fiction corpus using optimized NLP, with NER techniques, LDA modeling and LLM integration. After final commit, will be able to run a main file to generate a visualization of results on-demand. Modularized and documented code that can easily be reused/refitted for other kinds of corpii.
distilabel
⚗️ AI Feedback framework for scalable LLM alignment
fake-job-postings
llm2vec
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
Police-Killings-US
Exploratory analysis on a Washington Post database of police shootings between 2015-2022
sktime
A unified framework for machine learning with time series
langchain
🦜🔗 Build context-aware reasoning applications
kcentric's Repositories
kcentric/deep_nlp_on_sf_literature
Multi-pronged, multi-stage analysis of a 3.5M-sentences science fiction corpus using optimized NLP, with NER techniques, LDA modeling and LLM integration. After final commit, will be able to run a main file to generate a visualization of results on-demand. Modularized and documented code that can easily be reused/refitted for other kinds of corpii.
kcentric/argilla
✨Argilla: the open-source feedback platform for LLMs
kcentric/captions
transcripts and captions for 3blue1brown videos
kcentric/distilabel
⚗️ AI Feedback framework for scalable LLM alignment
kcentric/fake-job-postings
kcentric/llm2vec
Code for 'LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders'
kcentric/Police-Killings-US
Exploratory analysis on a Washington Post database of police shootings between 2015-2022
kcentric/sktime
A unified framework for machine learning with time series