-
Fin-LoRA Attack Demo
🛡Plant one sentence, watch a finance LoRA flip its call
-
LLM Safety Auditor
🔒Red-team any LLM against the OWASP LLM Top 10
-
Financial Sentiment FinBERT (small vs large)
📈Financial sentiment: MiniLM 33M vs DeBERTa-large 435M
-
Agent Autopsy
🔬Why did your LLM agent fail? Paste a trace, see the autopsy
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 3 minutes ago
9mark9/agent-autopsy-demo updated a collection 9 minutes ago
AI Safety & Fintech ML — live demos updated a model 9 minutes ago
9mark9/finbert-deberta-large-sentimentOrganizations
None yet
LLM red-teaming, agent observability, fairness audits, financial-sentiment LoRAs, compliance RAG and agent memory. Every demo runs real logic.
Small financial-sentiment models and attacks
LoRA and MiniLM classifiers for financial text, plus a demo of how a planted sentence can flip them.
- Running on ZeroAgents
Fin-LoRA Attack Demo
🛡Plant one sentence, watch a finance LoRA flip its call
-
9mark9/fin-lora-news-qwen2.5-1.5b-adv
Text Generation • 2B • Updated • 230 • 1 -
9mark9/fin-lora-news-qwen2.5-0.5b-adv
Text Generation • 0.5B • Updated • 340 - RunningAgents
Financial Sentiment FinBERT (small vs large)
📈Financial sentiment: MiniLM 33M vs DeBERTa-large 435M
Astronomy and science ML
A planet-candidate scorer trained on TESS data, with its results.
LLM security and agent tooling
Red-team prompts, a safety auditor with recorded real-model runs, agent failure analysis and an agent memory server.
- Running
LLM Safety Auditor
🔒Red-team any LLM against the OWASP LLM Top 10
-
9mark9/llm-redteam-owasp-prompts
Viewer • Updated • 150 • 138 • 1 - RunningAgents
Agent Autopsy
🔬Why did your LLM agent fail? Paste a trace, see the autopsy
- Running
Lethe Agent Memory
🧠Agent memory server that learns what to recall
Responsible AI and compliance demos
A fairness audit with regulatory thresholds and a retrieval demo over sample compliance documents.
AI Safety & Fintech ML — live demos
LLM red-teaming, agent observability, fairness audits, financial-sentiment LoRAs, compliance RAG and agent memory. Every demo runs real logic.
- Running on ZeroAgents
Fin-LoRA Attack Demo
🛡Plant one sentence, watch a finance LoRA flip its call
- Running
LLM Safety Auditor
🔒Red-team any LLM against the OWASP LLM Top 10
- RunningAgents
Financial Sentiment FinBERT (small vs large)
📈Financial sentiment: MiniLM 33M vs DeBERTa-large 435M
- RunningAgents
Agent Autopsy
🔬Why did your LLM agent fail? Paste a trace, see the autopsy
LLM security and agent tooling
Red-team prompts, a safety auditor with recorded real-model runs, agent failure analysis and an agent memory server.
- Running
LLM Safety Auditor
🔒Red-team any LLM against the OWASP LLM Top 10
-
9mark9/llm-redteam-owasp-prompts
Viewer • Updated • 150 • 138 • 1 - RunningAgents
Agent Autopsy
🔬Why did your LLM agent fail? Paste a trace, see the autopsy
- Running
Lethe Agent Memory
🧠Agent memory server that learns what to recall
Small financial-sentiment models and attacks
LoRA and MiniLM classifiers for financial text, plus a demo of how a planted sentence can flip them.
- Running on ZeroAgents
Fin-LoRA Attack Demo
🛡Plant one sentence, watch a finance LoRA flip its call
-
9mark9/fin-lora-news-qwen2.5-1.5b-adv
Text Generation • 2B • Updated • 230 • 1 -
9mark9/fin-lora-news-qwen2.5-0.5b-adv
Text Generation • 0.5B • Updated • 340 - RunningAgents
Financial Sentiment FinBERT (small vs large)
📈Financial sentiment: MiniLM 33M vs DeBERTa-large 435M
Responsible AI and compliance demos
A fairness audit with regulatory thresholds and a retrieval demo over sample compliance documents.
Astronomy and science ML
A planet-candidate scorer trained on TESS data, with its results.