ram-lexsi/circuitkit-jailbreak-steering-qwen2.5-1.5b-circuit
Updated
Ram Kadiyala
ram-lexsi
AI & ML interests
Interpretability, Explainability, Post-training
Recent Activity
new activity 6 days ago
Lexsi/Gemma-4-31B-it-Multilingual-Safety-Repair:Upload 4 files new activity 6 days ago
Lexsi/Gemma-4-31B-it-Cybersecurity-Safety-Repair:Upload 4 files new activity 6 days ago
Lexsi/Gemma-4-31B-it-Cybersecurity-Safety-Repair:Upload 5 filesOrganizations
models 73
ram-lexsi/agenttune-apigen-SFT-qwen3-0.6b
Text Generation • 0.6B • Updated • 124
ram-lexsi/agenttune-agent-ops-SFT-qwen3-0.6b
Updated
ram-lexsi/aligntune-qwen3-0.6b-drop-mc-curated
Updated
ram-lexsi/aligntune-qwen3-0.6b-drop-mc-full
Updated
ram-lexsi/out_agent_ops_sft
Updated
ram-lexsi/agenttune-agent-ops-GRPO
Updated
ram-lexsi/safetune-testrun-unlearn_rmu
Text Generation • 2B • Updated • 229
ram-lexsi/safetune-testrun-unlearn_simdpo
Text Generation • 2B • Updated • 353
ram-lexsi/safetune-testrun-unlearn_flat
Text Generation • 2B • Updated • 302
datasets 62
ram-lexsi/circuitkit-jailbreak-steering-qwen2.5-1.5b-results
Viewer • Updated • 5 • 102
ram-lexsi/agenttune-apigen-SFT-qwen3-0.6b-traces
Viewer • Updated • 64 • 61
ram-lexsi/agenttune-agent-ops-SFT-qwen3-0.6b-traces
Viewer • Updated • 504 • 89
ram-lexsi/aligntune-qwen3-0.6b-drop-mc-data
Viewer • Updated • 2.03k • 63
ram-lexsi/agenttune-agent-ops-GRPO-traces
Viewer • Updated • 800 • 80
ram-lexsi/agenttune-testrun-selfheal
Viewer • Updated • 10 • 59
ram-lexsi/agenttune-testrun-synthesis
Viewer • Updated • 6 • 68
ram-lexsi/agenttune-testrun-decide
Viewer • Updated • 1 • 70
ram-lexsi/agenttune-testrun-cli
Viewer • Updated • 1 • 83
ram-lexsi/agenttune-testrun-lm-eval
Viewer • Updated • 1 • 43