Pradheep1647/eagle3-speculative-decoding-policy
Reinforcement Learning • Updated
Pradheep
Pradheep1647
AI & ML interests
None yet
Recent Activity
liked a dataset 1 day ago
XiaomiMiMo/MiMo-V2.6-RL-oss updated a dataset 5 days ago
Pradheep1647/strictly-speaking published a dataset 5 days ago
Pradheep1647/strictly-speakingOrganizations
None yet
Pradheep1647/qwen2.5-coder-1.5b-lean-repository-midtraining
Text Generation • Updated • 12
Pradheep1647/qwen2.5-coder-1.5b-lean-language-sft
Text Generation • Updated • 7
Pradheep1647/q0-gsm8k-1_5b-mopd
Text Generation • 2B • Updated • 66
Pradheep1647/q0-gsm8k-1_5b-mixture-top2
Updated
Pradheep1647/q0-gsm8k-1_5b-grpo
Text Generation • 2B • Updated • 25
Pradheep1647/q0-gsm8k-135m-grpo
Text Generation • 0.1B • Updated • 119
Pradheep1647/q0-gsm8k-135m-mopd
Text Generation • Updated
Pradheep1647/q0-gsm8k-135m
Updated
Pradheep1647/q0-gsm8k-135m-baseline
Updated
Pradheep1647/qwen3-0.6b-gsm8k-opsd-fkl-r16-clip005-s800
Text Generation • Updated • 7
Pradheep1647/meeting_summarization_kda-meetingbank-bs8-e20-bf16-4
Updated • 4
Pradheep1647/kibitzer-tactical-repair
Reinforcement Learning • Updated
Pradheep1647/kibitzer-s2-shaw-142m-comp
Updated
Pradheep1647/kibitzer-s2-shaw-100m
Updated • 1
Pradheep1647/kibitzer-clean-joint-scratch
Updated
Pradheep1647/kibitzer-clean-value-repair-trunk1
Updated
Pradheep1647/kibitzer-clean-value-repair-norm
Updated
Pradheep1647/kibitzer-clean-value-repair
Updated
Pradheep1647/kibitzer-clean-joint-distill
Updated
Pradheep1647/kibitzer-clean-value
Updated
Pradheep1647/kibitzer-clean-policy
Updated
Pradheep1647/msa-meetingbank-paper-compare-new
Updated
Pradheep1647/msa-meetingbank-paper-compare-old
Updated
Pradheep1647/kibitzer-sft
Updated
Pradheep1647/kibitzer-distill-elo-minus-0058-step-001000
Updated
Pradheep1647/kibitzer-distill-elo-minus-0280-step-000500
Updated
Pradheep1647/kibitzer-az-elo-minus-0120-step-000020
Updated
Pradheep1647/kibitzer-az-elo-minus-0191-step-000015
Updated
Pradheep1647/kibitzer-az-elo-minus-0280-step-000005
Updated