xxccho/grpo_lg_convfin_mcq_grpo_ratio1.0_gen16_bs4_lr7e-6
Updated
cho changhee
xxccho
·
AI & ML interests
None yet
Recent Activity
published a dataset about 15 hours ago
xxccho/gsm8k_rmbench_style updated a dataset about 15 hours ago
xxccho/gsm8k_rmbench_style updated a model 1 day ago
xxccho/grpo_lg_convfin_mcq_grpo_ratio1.0_gen16_bs4_lr7e-6Organizations
models 12
xxccho/grpo_lg_convfin_mcq_grpo_ratio1.0_gen8_bs4_lr7e-6
Updated
xxccho/EXAONE-3.5-7.8B-Instruct-LGConvFinMCQ-ReasoningPC-SFT-LoRA
Updated
xxccho/EXAONE-3.5-7.8B-Instruct-LGConvFinMCQ-PC-SFT-LoRA
Updated
xxccho/EXAONE-3.5-7.8B-Instruct-convfinqa-SFT-LoRA
Updated
xxccho/EXAONE-3.5-7.8B-GRPO-LG-ConvFin-MCQ-numgen16
Text Generation • Updated • 13
xxccho/EXAONE-3.5-7.8B-Instruct-ConvFinQA-GRPO_PLAIN
Text Generation • Updated • 16
xxccho/EXAONE-3.5-7.8B-Instruct-LGConvFin-MCQ-GRPO_PLAIN
Text Generation • Updated
xxccho/EXAONE-3.5-7.8B-Instruct-ConvFinQA-SFT-GRPO
Text Generation • Updated • 6
xxccho/margin_reg_baseline_stem
Updated