udgamlabs
/

Laghu-Checkpoints

small-language-model

trained-from-scratch

research-release

training-dynamics

Model card Files Files and versions

Laghu-Checkpoints / rl-r1-failed /eval /math_think.jsonl

Commit History

Oct 21 6 days ago

19:19
Add rl-r1-failed/eval from udgamlabs/udgam3-rl

jiteshkprasad

Verified signature
9f7df6a