Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
SeanWang0027
/
rose-opd-implementation
Like
0
distillation
on-policy-distillation
rose
opd
verl
trinity
agentgym
rlve
sciworld
dapo
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
rose-opd-implementation
/
frameworks
/
slime
/
tests
172 kB
Ctrl+K
Ctrl+K
1 contributor
History:
1 commit
SeanWang0027
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
af66a85
verified
about 1 month ago
ci
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
plugin_contracts
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
utils
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_chunked_gae.py
Safe
1.91 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_gspo.sh
Safe
1.55 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_mimo_7B_mtp_only_grad.py
Safe
4.58 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_moonlight_16B_A3B.py
Safe
3.68 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_moonlight_16B_A3B_r3.py
Safe
3.72 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_quick_start_glm4_9B.py
Safe
3.76 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_async_short.py
Safe
3.35 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_debug_rollout_then_train.py
Safe
4.32 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_gsm8k_async_short.py
Safe
3.71 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_gsm8k_short.py
Safe
3.66 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_opd_sglang.py
Safe
6.71 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_ppo_critic_only_short.py
Safe
3.14 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_sglang_config.py
Safe
4.32 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_sglang_config_distributed.py
Safe
4.47 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen2.5_0.5B_short.py
Safe
3.3 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_0.6B_parallel_check.py
Safe
4.55 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_30B_A3B.py
Safe
4.72 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_30B_A3B_r3.py
Safe
4.73 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_4B_ckpt.py
Safe
4.23 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_4B_ppo.py
Safe
3.89 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_4B_ppo_train_critic_only.py
Safe
3.89 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_5_mtp_bridge_mapping.py
Safe
9.21 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_qwen3_linear_attention_cu_seqlens.py
Safe
5.92 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_sglang_config_mixed_offload.py
Safe
4.53 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago
test_sglang_config_mixed_offload_ft.py
Safe
4.68 kB
Vendor slime @ 26525f9, the trainer reopd_ref builds on (part 2)
about 1 month ago