Raw CommonCrawl crawls, annotated with Creative Commons license information
Bram Vanroy PRO
BramVanroy
AI & ML interests
Artificial intelligence, natural language processing, computational linguistics
Recent Activity
liked a Space 1 day ago
Rijgersberg/random-GPT-NL-document liked a model 1 day ago
ellamind/propella-1-4b new activity 1 day ago
openeurollm/propella-annotations:Dutch FineWeb 2 and HPLT3Organizations
SFT and DPO models for GEITje 7B Ultra, including the datasets used to train them.
A back-up on the hub of the BLEURT models (https://github.com/google-research/bleurt/blob/master/checkpoints.md)
An open and efficient LLM for Dutch based on phi-2
Older finetunes - not recommended!
-
Language Resources for Dutch Large Language Modelling
Paper • 2312.12852 • Published • 9 -
BramVanroy/Llama-2-13b-chat-dutch
Text Generation • 13B • Updated • 581 • 19 -
BramVanroy/llama2-13b-ft-mc4_nl_cleaned_tiny
Text Generation • 13B • Updated • 4 • 4 -
BramVanroy/falcon-40b-ft-alpaca-dolly-dutch
Text Generation • 41B • Updated • 13 • 4
Raw CommonCrawl crawls, annotated with Creative Commons license information
An open and efficient LLM for Dutch based on phi-2
SFT and DPO models for GEITje 7B Ultra, including the datasets used to train them.
Older finetunes - not recommended!
-
Language Resources for Dutch Large Language Modelling
Paper • 2312.12852 • Published • 9 -
BramVanroy/Llama-2-13b-chat-dutch
Text Generation • 13B • Updated • 581 • 19 -
BramVanroy/llama2-13b-ft-mc4_nl_cleaned_tiny
Text Generation • 13B • Updated • 4 • 4 -
BramVanroy/falcon-40b-ft-alpaca-dolly-dutch
Text Generation • 41B • Updated • 13 • 4
A back-up on the hub of the BLEURT models (https://github.com/google-research/bleurt/blob/master/checkpoints.md)