reproducing DeepSeek R1 Zero with Qwen2.5-0.5B on two 4090 GPUs
rasdani PRO
rasdani
AI & ML interests
None yet
Recent Activity
updated
a dataset
about 9 hours ago
rasdani/SkyRL-v0-293-data-oracle-8k-context
updated
a dataset
about 10 hours ago
rasdani/SkyRL-v0-293-data-oracle
updated
a dataset
3 days ago
rasdani/SWE-bench_Verified_oracle_32k_100
Organizations
models
35
rasdani/qwen3_8b_swe_rl_8k
8B
•
Updated
•
15
rasdani/deepseek_r1_7b_gh_patches_2k_fixed_reward
8B
•
Updated
•
9
rasdani/deepseek_r1_7b_gh_patches_2k
8B
•
Updated
•
11
rasdani/crux-eval_math-eval-logs
Updated
rasdani/git-diff-Qwen-4B-10k
4B
•
Updated
•
23
rasdani/git-diff-Qwen-4B-10k-checkpoints
Updated
rasdani/git-diff-Qwen-4B-32k-checkpoints
Updated
rasdani/git-diff-Qwen-4B-30k
4B
•
Updated
•
12
rasdani/git-diff-Qwen-4B
4B
•
Updated
•
79
rasdani/git-diff-Qwen-1.7B
2B
•
Updated
•
60
datasets
153
rasdani/SkyRL-v0-293-data-oracle-8k-context
Viewer
•
Updated
•
145
•
82
rasdani/SkyRL-v0-293-data-oracle
Viewer
•
Updated
•
316
•
61
rasdani/SWE-bench_Verified_oracle_32k_100
Viewer
•
Updated
•
100
•
43
rasdani/SWE-bench_Verified_oracle_32k_50
Viewer
•
Updated
•
50
•
30
rasdani/SWE-bench_Verified_oracle_32k_10
Viewer
•
Updated
•
20
•
29
rasdani/SWE-bench_Verified_oracle_32k
Viewer
•
Updated
•
930
•
74
rasdani/SWE-bench_Verified_oracle
Viewer
•
Updated
•
500
•
50
rasdani/SkyRL-v0-293-data-parsed-commits
Viewer
•
Updated
•
316
•
61
rasdani/SkyRL-v0-80-data-parsed-commits
Viewer
•
Updated
•
316
•
60
rasdani/SkyRL-v0-293-data
Viewer
•
Updated
•
316
•
60