reproducing DeepSeek R1 Zero with Qwen2.5-0.5B on two 4090 GPUs
rasdani
rasdani
AI & ML interests
None yet
Recent Activity
updated
a dataset
30 minutes ago
rasdani/reward-bench-2-if
published
a dataset
30 minutes ago
rasdani/reward-bench-2-if
updated
a dataset
about 1 hour ago
rasdani/github-patches-10k-sample-sorted
Organizations
Collections
1
Papers
1
models
23

rasdani/qwen3_0_6b_function_rm
Updated
•
16

rasdani/Qwen2.5-0.5B-simpleRL-Zoo-8192k
Updated
•
9

rasdani/Qwen2.5-0.5B-simpleRL-Zoo
Text Generation
•
Updated
•
6

rasdani/smolR1-Qwen2.5-0.5B
Text Generation
•
Updated
•
8

rasdani/Qwen2.5-0.5B-simpleRL-Zoo-no-KL
Updated

rasdani/Qwen2.5-0.5B-simpleRL-Zoo-3072k
Updated

rasdani/Qwen2.5-0.5B-simpleRL-Zoo-4096k
Updated

rasdani/Qwen2.5-0.5B-simpleRL-Zoo-2560k
Updated

rasdani/Qwen2.5-0.5B-simpleRL-Zoo-2048k
Updated

rasdani/Qwen2.5-0.5B-simpleRL-Zoo-first-try
Updated
•
3
datasets
105
rasdani/reward-bench-2-if
Viewer
•
Updated
•
160
rasdani/github-patches-10k-sample-sorted
Viewer
•
Updated
•
1.06k
rasdani/swe-fixer-20k-sample-sorted
Viewer
•
Updated
•
2k
rasdani/swe-fixer-10k-sample-sorted
Viewer
•
Updated
•
2k
rasdani/swe-fixer-4k-token-limit-sorted-2k
Viewer
•
Updated
•
2k
•
95
rasdani/swe-fixer-4k-token-limit-sorted
Viewer
•
Updated
•
54.3k
•
107
rasdani/swe-fixer-4k-token-limit
Viewer
•
Updated
•
54.3k
•
107
rasdani/swe-fixer-70k-filtered
Viewer
•
Updated
•
54.3k
•
72
rasdani/ifeval-genesys
Viewer
•
Updated
•
15k
•
48
rasdani/ifeval-genesys-verified
Viewer
•
Updated
•
48
•
48