solving Github issues with Agentless scaffold and RL
rasdani PRO
rasdani
AI & ML interests
None yet
Recent Activity
updated a model 14 days ago
rasdani/gemma-4-26B-A4B-it-PB published a model 14 days ago
rasdani/gemma-4-26B-A4B-it-PB authored a paper 16 days ago
Prime Agent: A Self-Improving RLM HarnessOrganizations
models 40
rasdani/gemma-4-26B-A4B-it-PB
26B • Updated • 13
rasdani/Laguna-XS-2.1-Step-1000
33B • Updated • 7
rasdani/Laguna-XS-2.1-Step-1000-GGUF-Q4_K_M
33B • Updated • 14
rasdani/deepseek_r1_qwen14b_swe_rl_8k
15B • Updated • 2 • 1
rasdani/deepseek_r1_llama_8b_swe_rl_8k_12_epochs
8B • Updated • 4 • 1
rasdani/qwen3_8b_swe_rl_8k
8B • Updated • 3
rasdani/deepseek_r1_7b_gh_patches_2k_fixed_reward
8B • Updated • 11
rasdani/deepseek_r1_7b_gh_patches_2k
8B • Updated • 10
rasdani/crux-eval_math-eval-logs
Updated
rasdani/git-diff-Qwen-4B-10k
4B • Updated • 3
datasets 177
rasdani/deepcoder_eval_claude-sonnet-4-20250514
Viewer • Updated • 16 • 9
rasdani/Code-Contests-Plus-HQ-2x-GRPO
Viewer • Updated • 5.36k • 15
rasdani/Code-Contests-Plus-HQ-1x-GRPO
Viewer • Updated • 4.55k • 34
rasdani/fill-cup-merged
Viewer • Updated • 9.73k • 9
rasdani/SWE-bench_Verified_oracle-parsed_commits_32k_5
Viewer • Updated • 5 • 64
rasdani/SWE-bench_Verified_oracle-parsed_commits_32k_2
Viewer • Updated • 2 • 56
rasdani/SWE-Bench-Verified-R2E-Gym-100
Viewer • Updated • 100 • 46
rasdani/SkyRL-v0-293-data-oracle-4k-context-100-epochs
Viewer • Updated • 7.2k • 8
rasdani/SkyRL-v0-293-data-oracle-8k-context-100-epochs
Viewer • Updated • 13.1k • 11
rasdani/deepseek_r1_llama_8b_swe_rl_8k_12_epochs_preds_100_v2
Viewer • Updated • 100 • 11