Red-team prompts, a safety auditor with recorded real-model runs, agent failure analysis and an agent memory server.
Nagizaaz Shaik PRO
9mark9
AI & ML interests
Generative AI Engineer · Agentic AI · RAG · AWS · Fintech. LLM gateways, agent memory, LoRA fine-tuning, and AI-agent security research. AWS ML Specialty.
Recent Activity
updated a Space about 21 hours ago
9mark9/rag-compliance-intelligence-demo updated a Space about 21 hours ago
9mark9/ml-fairness-audit-demo updated a Space about 21 hours ago
9mark9/lethe-agent-memoryOrganizations
None yet
LoRA and MiniLM classifiers for financial text, plus a demo of how a planted sentence can flip them.
-
Fin-LoRA Attack Demo
🛡Plant one sentence, watch a financial sentiment LoRA flip
-
9mark9/fin-lora-news-qwen2.5-1.5b-adv
Text Generation • Updated • 80 • 1 -
9mark9/fin-lora-news-qwen2.5-0.5b-adv
Text Generation • Updated • 219 -
Financial Sentiment FinBERT MiniLM
📈Financial sentence sentiment from a 33M-parameter MiniLM
Red-team prompts, a safety auditor with recorded real-model runs, agent failure analysis and an agent memory server.
LoRA and MiniLM classifiers for financial text, plus a demo of how a planted sentence can flip them.
-
Fin-LoRA Attack Demo
🛡Plant one sentence, watch a financial sentiment LoRA flip
-
9mark9/fin-lora-news-qwen2.5-1.5b-adv
Text Generation • Updated • 80 • 1 -
9mark9/fin-lora-news-qwen2.5-0.5b-adv
Text Generation • Updated • 219 -
Financial Sentiment FinBERT MiniLM
📈Financial sentence sentiment from a 33M-parameter MiniLM
spaces 7
pinned
Running
Agents
ML Fairness Audit
⚖
ECOA fairness audit — disparate impact & bias detection
pinned
Running
Lethe Agent Memory
🧠
Memory server for AI agents that learns what to recall
pinned
Running
Agents
Financial Sentiment FinBERT MiniLM
📈
Financial sentence sentiment from a 33M-parameter MiniLM
pinned
Running
Agents
Agent Autopsy
🔬
Post-mortems for failing LLM agents
pinned
Running on Zero
Agents
Fin-LoRA Attack Demo
🛡
Plant one sentence, watch a financial sentiment LoRA flip
pinned
Sleeping
LLM Safety Auditor
🔒
Red-team LLMs — adversarial attacks, OWASP Top 10
models 7
9mark9/fin-lora-news-qwen2.5-0.5b-adv
Text Generation • Updated • 219
9mark9/finbert-minilm-sentiment
Text Classification • 33.4M • Updated • 405
9mark9/exoscout-tess-planet-scorer
Tabular Classification • Updated
9mark9/fin-lora-news-qwen2.5-1.5b
Text Generation • Updated • 135 • 1
9mark9/fin-lora-news-qwen2.5-1.5b-adv
Text Generation • Updated • 80 • 1
9mark9/fin-lora-news-qwen2.5-0.5b
Text Generation • Updated • 404 • 1
9mark9/finbert-deberta-large-sentiment
Text Classification • 0.4B • Updated • 106