AI & ML interests

transformation

Recent Activity

ValiantLabs's activity

sequelbox 
posted an update about 7 hours ago
view post
Post
330
SNEAK PREVIEW: Tachibana 2! A new high-difficulty code-reasoning dataset to use and challenge deepseek-ai/DeepSeek-R1 - harder prompts, complex requirements, deeper technical skill.

Link here: sequelbox/Tachibana2-DeepSeek-R1-PREVIEW

All responses generated by DeepSeek's R1 model, all prompts synthetically generated by Llama 3.1 405b Instruct.

excited to bring out the full dataset for everyone's use as soon as I can! more to come soon.
sequelbox 
posted an update 14 days ago
sequelbox 
posted an update 21 days ago
view post
Post
1899
New sneak preview of my next release! Raiden is a deepseek-ai/DeepSeek-R1 synthetic dataset that uses creative-reasoning and analytic-reasoning prompts!

This preview release has the first 5.8k rows, all responses generated using DeepSeek's 685b parameter R1 model: sequelbox/Raiden-DSR1-PREVIEW

Enjoy this look at R1's reasoning skills! Full dataset coming soon.
sequelbox 
posted an update about 1 month ago
view post
Post
2357
A general FYI that Valiant Labs no longer has an X account. This is a business decision. Many other businesses seem to be making the same decision right now.

You can follow my account on Bluesky for updates on Shining Valiant 3, other Valiant Labs models, my open-source datasets, etc: https://bsky.app/profile/sequelbox.bsky.social

back to building :)
sequelbox 
updated a Space about 1 month ago