-
oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 159 -
oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 34 -
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 109 -
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 95
Miao Li
oaimli
AI & ML interests
Natural Language Processing
Recent Activity
updated a model 3 days ago
oaimli/sft_longpt_full_qwen3_4b_instruct_2507 published a model 3 days ago
oaimli/sft_longpt_full_qwen3_4b_instruct_2507 updated a model 4 days ago
oaimli/sft_longpt_full_gemma3_4b_itOrganizations
None yet
-
oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 159 -
oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 34 -
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 109 -
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 95
Long-context post-training
models 37
oaimli/sft_longpt_full_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 783 • 1
oaimli/sft_longpt_full_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 343
oaimli/sft_longpt_full_qwen3_4b_instruct_2507_no_starting_think
Text Generation • 4B • Updated • 8
oaimli/sft_longpt_full_gemma3_4b_it_no_starting_think
Image-Text-to-Text • 4B • Updated • 1
oaimli/grpo_longpt_direct_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 13
oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_660
Text Generation • 4B • Updated • 31
oaimli/scitrek_grpo_full_longrlvr_qwen3_4b_instruct_2507_280
Text Generation • 4B • Updated • 64
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 95
oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 161
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 109