diff --git a/examples/scripts/grpo_vlm.py b/examples/scripts/grpo_vlm.py index 858508ad126..5e92d5bf668 100644 --- a/examples/scripts/grpo_vlm.py +++ b/examples/scripts/grpo_vlm.py @@ -46,7 +46,7 @@ --log_completions # For HuggingFaceTB/SmolVLM2-2.2B-Instruct -pip install num2words +pip install num2words==0.5.14 accelerate launch \ --config_file examples/accelerate_configs/deepspeed_zero3.yaml \ diff --git a/examples/scripts/gspo.py b/examples/scripts/gspo.py index 6a89f876cef..31dd4a98784 100644 --- a/examples/scripts/gspo.py +++ b/examples/scripts/gspo.py @@ -27,7 +27,7 @@ pip install math_verify # For Qwen/Qwen3-0.6B -pip install num2words +pip install num2words==0.5.14 accelerate launch \ --config_file examples/accelerate_configs/deepspeed_zero3.yaml \ diff --git a/examples/scripts/online_dpo_vlm.py b/examples/scripts/online_dpo_vlm.py index 78b2a89dc1d..39246bb4209 100644 --- a/examples/scripts/online_dpo_vlm.py +++ b/examples/scripts/online_dpo_vlm.py @@ -47,7 +47,7 @@ --gradient_accumulation_steps 2 # For HuggingFaceTB/SmolVLM2-2.2B-Instruct -pip install num2words +pip install num2words==0.5.14 accelerate launch \ --config_file examples/accelerate_configs/deepspeed_zero3.yaml \ diff --git a/examples/scripts/rloo.py b/examples/scripts/rloo.py index 7101f4e6586..e9fb222f63b 100644 --- a/examples/scripts/rloo.py +++ b/examples/scripts/rloo.py @@ -25,7 +25,7 @@ # /// """ -pip install math_verify num2words peft trackio vllm +pip install math_verify num2words==0.5.14 peft trackio vllm export TRACKIO_PROJECT="RLOO-NuminaMath-TIR" accelerate launch --config_file examples/accelerate_configs/deepspeed_zero3.yaml examples/scripts/rloo.py """ diff --git a/setup.cfg b/setup.cfg index df51313f944..fa431a70501 100644 --- a/setup.cfg +++ b/setup.cfg @@ -73,7 +73,7 @@ vllm = vlm = Pillow torchvision - num2words + num2words==0.5.14 dev = %(bco)s %(deepspeed)s