zswzswzsw
/

verl_subquestion

Model card Files Files and versions

verl_subquestion / examples /ppo_trainer

54.2 kB

1 contributor

History: 1 commit

zswzswzsw's picture

Upload folder using huggingface_hub

66407c5 verified about 2 months ago

README.md

6.63 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek7b_llm.sh

1.8 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek7b_llm_modelscope.sh

1.82 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek7b_llm_pfppo.sh

1.98 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek7b_llm_sandbox_fusion.sh

2.04 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek7b_llm_sp2.sh

1.91 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek_full_hh_rlhf.sh

1.79 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek_math_gsm8k_megatron.sh

2.27 kB

Upload folder using huggingface_hub about 2 months ago
run_deepseek_math_gsm8k_megatron_nsys.sh

3.14 kB

Upload folder using huggingface_hub about 2 months ago
run_gemma.sh

1.69 kB

Upload folder using huggingface_hub about 2 months ago
run_moonlight16b_a3b_gsm8k_megatron.sh

5.03 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen1.5_moe_a2.7b-gsm8k_megatron.sh

3.26 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2-7b_math_gsm8k_megatron.sh

2.21 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2-7b_rm.sh

3.11 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2-7b_rm_seq_balance.sh

2.55 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2-7b_rm_seq_balance_fused_kernels.sh

2.76 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2-7b_rm_seq_balance_nsys.sh

3.5 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2-7b_seq_balance.sh

2.45 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2-7b_sglang_seq_balance.sh

2.15 kB

Upload folder using huggingface_hub about 2 months ago
run_qwen2.5-32b.sh

2.11 kB

Upload folder using huggingface_hub about 2 months ago