a-t-c-g

there are plenty of OSS finetuned models + base models around. If you're looking for doing these on your own dataset, worth getting in touch with cartesien.io or wire up https://github.com/SalesforceAIResearch/PretrainRL-pipeline

natural language may provide part of the scaffolding for reasoning, but the capability itself seems to depend more on learned transformations over internal representations than on language alone

refs: https://arxiv.org/abs/2412.17819 https://arxiv.org/abs/2412.06769

Yes - some degree of reasoning appears to be latent in the structure of language itself. But models trained explicitly on reasoning-focused data still perform better than models trained only on general corpora.*

*At least up to 300B parameters, based on the models we’ve tested.

Benchmarks, we have internal ones testing reasoning fine-tuned v/s frontier + prompts

For some use cases it can be parity performance at 1/20th the cost up to exceeds at 1/10th the cost. Trade-off is ofc narrow applicability

The quality of custom models trained with proper reasoning datasets[0] even with small parameters (3-7B is sweet spot) is incredible now

[0]: cartesien.io or Salesforce's WebscaleRL