VladShash/qwen3-8b-classic-with-SFT-replay-grpo-250
8B • Updated • 40
Vladyslav Shashkov
VladShash
·
AI & ML interests
None yet
Recent Activity
updated a dataset 3 days ago
VladShash/formalmathatepfl_feedback-grpo-reasoning-sft_minif2f_20261104_073844_raw.json published a dataset 3 days ago
VladShash/formalmathatepfl_feedback-grpo-reasoning-sft_minif2f_20261104_073844_raw.json updated a dataset 3 days ago
VladShash/formalmathatepfl_feedback-grpo-reasoning-sft_minif2f_20261104_073826_raw.jsonOrganizations
VladShash/qwen3-4b-classic-with-SFT-replay-grpo-275
4B • Updated • 22
VladShash/qwen3-4b-feedback-with-repair-grpo-200
4B • Updated • 10
VladShash/qwen3-4b-feedback-with-repair-grpo-150
4B • Updated • 7
VladShash/qwen3-4b-feedback-with-repair-distilled
Text Generation • 4B • Updated • 844
VladShash/qwen3-8b-feedback-no-repair-grpo-175-alt
8B • Updated • 5
VladShash/qwen3-8b-feedback-no-repair-grpo-175
8B • Updated • 60
VladShash/checkpoint-feedback-non-base-with-repair
8B • Updated • 3
VladShash/qwen3-8b-feedback-with-repair-distilled
Text Generation • 8B • Updated • 119
VladShash/checkpoint-sft-feedback-with-repair
8B • Updated • 7
VladShash/qwen3-8b-feedback-no-repair-grpo-50
8B • Updated • 5
VladShash/qwen3-8b-feedback-no-repair-distilled
Text Generation • 8B • Updated • 124
VladShash/checkpoint_feedback_no_repair
8B • Updated • 3
VladShash/qwen3-4b-feedback-no-repair
Text Generation • 4B • Updated • 10
VladShash/checkpoint-4b-feedback-no-repair
4B • Updated • 10
VladShash/qwen3-8b-classic-no-repair
Text Generation • 8B • Updated • 8
VladShash/checkpoint-8b-classic-no-repair
8B • Updated • 4
VladShash/qwen3-4b-feedback-with-repair
Text Generation • 4B • Updated • 31
VladShash/checkpoint-4b-feedback
4B • Updated • 5
VladShash/qwen3-8b-classic-with-repair
Text Generation • 8B • Updated • 20
VladShash/checkpoint-8b-classic
8B • Updated • 4
VladShash/qwen3-feedback-grpo-fl0.0-other_reward-step360
8B • Updated • 5
VladShash/qwen3-feedback-grpo-fl0.0-step460
8B • Updated • 3
VladShash/qwen3-feedback-grpo-fl0.05-step450
8B • Updated • 7
VladShash/qwen3-feedback-grpo-fl0.05-step420
8B • Updated • 3
VladShash/qwen3-feedback-grpo-fl0.0-step320
8B • Updated • 12
VladShash/qwen3-feedback-grpo-fl0.05-step310
8B • Updated • 5
VladShash/qwen3-feedback-grpo-fl0.05-step320
8B • Updated • 7
VladShash/qwen3-feedback-grpo-fl0.0-step220
8B • Updated • 3
VladShash/qwen3-feedback-grpo-fl0.05-step230
8B • Updated • 4