-
secmlr/patchpilot_qwen_code_7B_test_swe_reasoning
Text Generation • 8B • Updated • 4 -
secmlr/patchpilot_qwen_code_7B_test_swe_reasoning_short_llm
Text Generation • 8B • Updated • 6 -
secmlr/SWE-BENCH-400-reasoning-short-llm_qwen_code_32B_test_swe
Text Generation • 33B • Updated • 4 -
secmlr/SWE-BENCH-400-planning-claude_qwen_code_7B_test_swe_claude_planning
Text Generation • 8B • Updated • 5
UCSB-MLSEC
university
AI & ML interests
None defined yet.
Recent Activity
View all activity
-
secmlr/patchpilot_qwen_code_7B_test_swe_reasoning
Text Generation • 8B • Updated • 4 -
secmlr/patchpilot_qwen_code_7B_test_swe_reasoning_short_llm
Text Generation • 8B • Updated • 6 -
secmlr/SWE-BENCH-400-reasoning-short-llm_qwen_code_32B_test_swe
Text Generation • 33B • Updated • 4 -
secmlr/SWE-BENCH-400-planning-claude_qwen_code_7B_test_swe_claude_planning
Text Generation • 8B • Updated • 5
models
152
secmlr/split_context
8B
•
Updated
•
3
secmlr/best_n_no_rationale_poc_agent_withjava_final_model_agent_h100_64step_5epoch
Text Generation
•
8B
•
Updated
•
18
secmlr/best_n_no_rationale_poc_agent_withjava_final_model_agent_h100
Text Generation
•
8B
•
Updated
•
44
secmlr/best_n_rationale_poc_agent_withjava_final_model_agent
Text Generation
•
8B
•
Updated
•
17
secmlr/best_n_no_rationale_poc_agent_withjava_final_model_agent
Text Generation
•
8B
•
Updated
•
22
secmlr/best_n_rationale_poc_agent_final_model_agent_train
Text Generation
•
8B
•
Updated
•
5
secmlr/best_n_no_rationale_poc_agent_final_model_agent_train
Text Generation
•
8B
•
Updated
•
5
secmlr/final_model_nopolicy
Text Generation
•
8B
•
Updated
•
126
secmlr/Qwen3-pi-ft-0.6b
0.6B
•
Updated
•
2
secmlr/SWE-BENCH-433-enriched-set-claude-3in1-localization-with-reasoning_qwen_code_0.5b_433_enriched
Text Generation
•
0.5B
•
Updated
•
842
datasets
72
secmlr/best_n_no_rationale_poc_agent_withjava
Viewer
•
Updated
•
8.77k
•
27
secmlr/dsr1_clean_dataset_ds_correct_together-deepseek-reasoner_train_len_32000_inputlen_16000_n
Viewer
•
Updated
•
5.1k
•
8
secmlr/dsr1_ossfuzz_dataset_ds_correct_QwQ-32B_train_len_32000_inputlen_16000_n
Viewer
•
Updated
•
683
•
9
secmlr/dsr1_noisy_dataset_ds_correct_QwQ-32B_small_train_len_32000_inputlen_16000_n
Viewer
•
Updated
•
2.72k
•
12
secmlr/dsr1_clean_dataset_ds_correct_QwQ-32B_train_len_32000_inputlen_16000_n
Viewer
•
Updated
•
5.07k
•
10
secmlr/dsr1_noisy_dataset_ds_correct_together-deepseek-reasoner_small_train_len_32000_inputlen_16000_n
Viewer
•
Updated
•
2.91k
•
12
secmlr/dsr1_ossfuzz_dataset_ds_correct_together-deepseek-reasoner_train_len_32000_inputlen_16000_n
Viewer
•
Updated
•
723
•
10
secmlr/SURFI-p1_433_enriched__3in1_reasoning
Viewer
•
Updated
•
1.49k
•
11
secmlr/clean_dataset_ds_correct_QwQ-32B_java_len_32000_inputlen_16000
Viewer
•
Updated
•
181
•
12
secmlr/clean_dataset_ds_correct_together-deepseek-reasoner_java_len_32000_inputlen_16000
Viewer
•
Updated
•
197
•
10