use the general purpose LLM for the math task instead of code LLM. --------- Co-authored-by: Your Name <you@example.com>
Name |
Last commit
|
Last update |
---|---|---|
.. | ||
run_deepseek7b_llm.sh | Loading commit data... | |
run_deepseek7b_llm_sp2.sh | Loading commit data... | |
run_deepseek_full_hh_rlhf.sh | Loading commit data... | |
run_deepseek_math_gsm8k_megatron.sh | Loading commit data... | |
run_deepseek_megatron.sh | Loading commit data... | |
run_gemma.sh | Loading commit data... | |
run_qwen2-7b.sh | Loading commit data... | |
run_qwen2-7b_rm.sh | Loading commit data... | |
run_qwen2-7b_rm_seq_balance.sh | Loading commit data... | |
run_qwen2-7b_seq_balance.sh | Loading commit data... | |
run_qwen2.5-32b.sh | Loading commit data... | |
verl_getting_started.ipynb | Loading commit data... |