Name	Name	Last commit message	Last commit date
parent directory ..
qwen3-8b-actor-verifier-m2po-delta-dapo-data	qwen3-8b-actor-verifier-m2po-delta-dapo-data
qwen3-8b-actor-verifier-m2po-delta-deepscaler-data	qwen3-8b-actor-verifier-m2po-delta-deepscaler-data
qwen3-8b-actor-verifier-m2po-delta-no-ds-dapo-data	qwen3-8b-actor-verifier-m2po-delta-no-ds-dapo-data
qwen3-8b-actor-verifier-m2po-delta-no-ds-deepscaler-data	qwen3-8b-actor-verifier-m2po-delta-no-ds-deepscaler-data
qwen3-8b-single-agent-m2po-delta-dapo-data	qwen3-8b-single-agent-m2po-delta-dapo-data
qwen3-8b-single-agent-m2po-delta-deepscaler-data	qwen3-8b-single-agent-m2po-delta-deepscaler-data
qwen3-8b-single-agent-m2po-delta-no-ds-dapo-data	qwen3-8b-single-agent-m2po-delta-no-ds-dapo-data
qwen3-8b-single-agent-m2po-delta-no-ds-deepscaler-data	qwen3-8b-single-agent-m2po-delta-no-ds-deepscaler-data
README.md	README.md

Name

Last commit message

Last commit date

Math Multi-Agent Recipes

Math multi-agent recipes cover actor/verifier and related multi-model math training workflows.

Run one example from the repo root:

bash examples/math-multi-agent/qwen3-8b-actor-verifier-m2po-delta-deepscaler-data/scripts/run_qwen3-8b-actor-verifier-m2po-delta-deepscaler-data.sh

GPU Resources

These recipes default to one 8xH100 node.

Navigation Menu