Viewing profile — kumama

cheaper in terms of token costs

castform founder here. it uses lakebases's native bm25 and vector search and fuses the results using rrf ( https://medium.com/@devalshah1619/mathematical-intuition-beh... )

yup! email sent!

castform founder here. unfortunately, we are cloud-hosted at this point. but some easy options on the open-source side include huggingface's trl & unsloth. you can run our data-gen…

yup! it’s mostly about getting better at using the right search keywords. for more complex multi-hop question, it's also about knowing which sections of a document to look up and i…

+1 on SID-1. we were definitely inspired by that paper

very useful questions here! - if you have teams that have totally different documentation patterns, yes i think a model trained one teams' docs probably won't directly transfer to …

castform founder here. i'm personally a little against techniques like self-consistency/majority voting during rl training because they tend to result in the model's output distrib…

castform founder here. i'd say it's a threat but the frontier ai labs' argument would basically be that the market opportunity for intelligence is infinite so it doesn't matter. at…

the bigger model would still cost more :) at the same time, i see prompting as being orthogonal to post-training. i'd imagine post-training a smaller model with a better prompt wou…

(founder of castform here) the model you post-train should ideally learn general patterns & search strategies over your dataset that should transfer to new docs you add to the sear…

it's apache 2.0: https://github.com/castform-ai/benchmax/tree/main?tab=Apache...

for the example here the chunking is section aware -> but the general training data synthesis pipeline is agnostic to type of chunking

castform founder here. the roi optimization makes sense. i think there are lots of usecases for which even a 2% gain in accuracy can be quite useful. off the top of my head - high …

castform founder here. we should have made it more prominent on the blog but here's the full code example: https://github.com/castform-ai/benchmax/tree/main/examples/n...

this is really cool. i'm sure some of the larger e-commerce companies are already using clickstream data to tune better query rewriters/ranking models

castform founder here. openai actually deprecated their finetuning apis a few months back weirdly.

castform founder here. while it's "rare for a specialized model to beat a strong general model" today, i think the tech/knowhow on how to do so is getting there. we see some early …

castform founder here. that's a future we are really excited about too :) ideally, you can post-train the llm within the application itself, as it's being used. both interesting in…

castform founder here. despite our bet on fine-tuned smaller open-source models, i'm still quite bullish on the big labs. i think scaled closed models will continue to dominate for…

(castform founder here) we should have made it more prominent on the blogpost but here's the github repo: https://github.com/castform-ai/benchmax/tree/main/examples/n...

castform founder here: totally! we also think model routing is also a post-training problem i.e. getting a model to predict the difficulty of a task and match it to the right model…

(one of the blog post authors here) -> once you set up a finetuning pipeline, it's often trivial to rerun it on top of a new open weights model. so, it's orthogonal to base model i…