-
oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 385 -
oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 80 -
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 211 -
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated
Miao Li
oaimli
AI & ML interests
Natural Language Processing
Recent Activity
updated a collection about 17 hours ago
PGPO updated a model about 17 hours ago
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it published a model about 17 hours ago
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_itOrganizations
None yet
PGPO
-
oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 385 -
oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 80 -
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 211 -
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated
LongPT
Long-context post-training
models 30
oaimli/pgpo_grpo_proxy_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated
oaimli/scitrek_grpo_full_loongrl_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 325
oaimli/pgpo_grpo_proxy_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 211
oaimli/longtune_scitrek_grounding_reinforcement_gemma_0
Image-Text-to-Text • 4B • Updated • 40
oaimli/longtune_scitrek_simple_sft_gemma
Image-Text-to-Text • 4B • Updated • 66
oaimli/longtune_scitrek_simple_sft_qwen
Text Generation • 4B • Updated • 163
oaimli/pgpo_grpo_full_scitrek_gemma3_4b_it
Image-Text-to-Text • 4B • Updated • 80
oaimli/pgpo_grpo_full_scitrek_qwen3_4b_instruct_2507
Text Generation • 4B • Updated • 385
oaimli/scitrek_qwen25_7b_instruct_1m_sft_input_length
Text Generation • 8B • Updated • 144
oaimli/scitrek_qwen25_7b_instruct_1m_grpo_curriculum_192
Text Generation • 8B • Updated • 127