🤔 ..

Pradheep

Pradheep1647

25

·

https://www.pradheep.dev

AI & ML interests

None yet

Recent Activity

updated a dataset about 5 hours ago

Pradheep1647/lean-verifier-formalizations

liked a model 7 days ago

Nanbeige/Nanbeige4.3-33B-Base

liked a model 7 days ago

Nanbeige/Nanbeige4.3-33B

View all activity

Organizations

None yet

Pradheep1647 's models 105

Pradheep1647/grpo-think-len-concave

Updated 21 days ago • 37

Pradheep1647/grpo-think-len-capped-linear

Updated 21 days ago • 37

Pradheep1647/grpo-think-len-baseline

Updated 21 days ago • 35

Pradheep1647/jevlike-qwen3.5-2b-option-scorer-cached

Text Classification • Updated 28 days ago

Pradheep1647/jevlike-qwen3.5-2b-option-scorer-independent

Text Classification • Updated 28 days ago

Pradheep1647/jevlike-qwen3.5-2b-lora

Text Generation • Updated 29 days ago • 33

Pradheep1647/eagle3-speculative-decoding-policy

Reinforcement Learning • Updated Aug 16

Pradheep1647/qwen2.5-coder-1.5b-lean-repository-midtraining

Text Generation • Updated Aug 16 • 6

Pradheep1647/qwen2.5-coder-1.5b-lean-language-sft

Text Generation • Updated Aug 14 • 5

Pradheep1647/q0-gsm8k-1_5b-mopd

Text Generation • 2B • Updated Aug 13 • 8

Pradheep1647/q0-gsm8k-1_5b-mixture-top2

Pradheep1647/q0-gsm8k-1_5b-grpo

Text Generation • 2B • Updated Aug 11 • 8

Pradheep1647/q0-gsm8k-135m-grpo

Text Generation • 0.1B • Updated Aug 10 • 9

Pradheep1647/q0-gsm8k-135m-mopd

Text Generation • Updated Aug 9

Pradheep1647/q0-gsm8k-135m

Pradheep1647/q0-gsm8k-135m-baseline

Pradheep1647/qwen3-0.6b-gsm8k-opsd-fkl-r16-clip005-s800

Text Generation • Updated Aug 3 • 8

Pradheep1647/meeting_summarization_kda-meetingbank-bs8-e20-bf16-4

Updated Jul 28 • 4

Pradheep1647/kibitzer-tactical-repair

Reinforcement Learning • Updated Jul 14

Pradheep1647/kibitzer-s2-shaw-142m-comp

Pradheep1647/kibitzer-s2-shaw-100m

Updated Jul 6 • 1

Pradheep1647/kibitzer-clean-joint-scratch

Pradheep1647/kibitzer-clean-value-repair-trunk1

Pradheep1647/kibitzer-clean-value-repair-norm

Pradheep1647/kibitzer-clean-value-repair

Pradheep1647/kibitzer-clean-joint-distill

Pradheep1647/kibitzer-clean-value

Pradheep1647/kibitzer-clean-policy

Pradheep1647/msa-meetingbank-paper-compare-new

Pradheep1647/msa-meetingbank-paper-compare-old