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
11 minutes ago
rasdani/SWE-bench_Verified_oracle-parsed_commits_32k_100
published
a dataset
12 minutes ago
rasdani/SWE-bench_Verified_oracle-parsed_commits_32k_100
updated
a dataset
31 minutes ago
rasdani/SWE-bench_oracle-parsed-commits_100