arxiv:2602.13294
Jiarong Liang
lllqaq
AI & ML interests
Large Language Models (LLMs)
Natural Language Processing (NLP)
Recent Activity
updated
a model 1 day ago
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-merged_bucketab_4sources_11_epochs468 published
a model 1 day ago
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-merged_bucketab_4sources_11_epochs468 updated
a model 3 days ago
lllqaq/R2EGym-7B-Agent-Coder-Instruct1-merged_bucketab_4sources_sweep Organizations
models 28
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-merged_bucketab_4sources_11_epochs468
Updated
lllqaq/R2EGym-7B-Agent-Coder-Instruct1-merged_bucketab_4sources_sweep
Updated
lllqaq/R2EGym-32B-Agent-Coder-Instruct_merged_bucketab_4sources_20260228_101548_32768_8gpu
Text Generation • 1.12M • Updated
• 14
lllqaq/R2EGym-7B-Agent-Coder-Instruct-merged_bucketab_4sources_20260228_101548_32768_3gpu_oomfix
Text Generation • 333k • Updated
• 38
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-traj_reward1_loose_4sources_shuf42_ckpt2400
841k • Updated
• 11
lllqaq/R2EGym-14B-Agent-Coder-Instruct1-merged_bucketab_4sources_20260228_101548_32768_4gpu_oomfix
Text Generation • 841k • Updated
• 14
lllqaq/R2EGym-14B-Agent-Coder-Instruct-traj_bucketAB_multi_3sources_bucketAB_sft_shuf42
Text Generation • 841k • Updated
• 12
lllqaq/R2EGym-32B-Agent-Coder-Instruct-fimMidPostV2-r2egym-32k-ckpt808
1.12M • Updated
• 10
lllqaq/R2EGym-14B-Agent-Coder-Instruct-trajmix-gpt5miniAB-claude45AB-r2egymSFT-shuf42-32k-8gpu-oomfix
Text Generation • 841k • Updated
• 11
lllqaq/R2EGym-32B-Agent-Coder-Instruct-fim_midtrain_data_0108_212k_posttrain_r2egym_32768_8gpu
Text Generation • 1.12M • Updated
• 14