Keep on to blur preview images; turn off to show them clearly
It’s always at least 12 months behind
Code & LLMs. Working on document extraction: https://t.co/WREWHG95hE
“Open source is now only 12 months behind”
Code & LLMs. Working on document extraction: https://t.co/WREWHG95hE
“Open source is now only 12 months behind”
It’s always at least 12 months behind
I’ve had very little success fine tuning over gpt-oss models and very much success with qwen3 models (even the instruction versions). Not sure if this is a case of skill issue or what, but they are not as friendly to tuning
Code & LLMs. Working on document extraction: https://t.co/WREWHG95hE
RT @rosinality: FP16 can have a smaller training-inference gap compared to BFloat16, thus fits better for RL. Even the difference between R…
Code & LLMs. Working on document extraction: https://t.co/WREWHG95hE
RT @eliebakouch: Training LLMs end to end is hard. Very excited to share our new blog (book?) that cover the full pipeline: pre-training, p…
Code & LLMs. Working on document extraction: https://t.co/WREWHG95hE