-
CyberSecEvalTest
📈71Evaluate LLMs' cybersecurity risks and capabilities
-
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 35.4k • • 257 -
meta-llama/Prompt-Guard-86M
Text Classification • 0.3B • Updated • 23.4k • • 295 -
protectai/deberta-v3-base-prompt-injection-v2
Text Classification • 0.2B • Updated • 166k • • 82
Shyam Sunder Kumar
theainerd
AI & ML interests
Natural Language Processing
Recent Activity
liked
a model
4 days ago
nvidia/nemotron-speech-streaming-en-0.6b
liked
a dataset
9 days ago
futurehouse/lab-bench
updated
a collection
21 days ago
Safety & Security
Organizations
-
Agent Laboratory: Using LLM Agents as Research Assistants
Paper • 2501.04227 • Published • 95 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 102 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 109 -
Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments
Paper • 2501.10893 • Published • 26
Utils useful for LLM
-
Predict Memory
🧮102Calculate memory usage for model configurations
-
Model Memory Utility
🚀996Calculate vRAM needed for model training and inference
-
Transformers Timeline
🤗68Interactive timeline to explore the 🤗Transformers models
-
The Smol Training Playbook
📚2.83kThe secrets to building world-class LLMs
-
Training Large Language Models to Reason in a Continuous Latent Space
Paper • 2412.06769 • Published • 92 -
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Paper • 2408.03314 • Published • 63 -
Evolving Deeper LLM Thinking
Paper • 2501.09891 • Published • 115 -
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper • 2501.12599 • Published • 126
-
CyberSecEvalTest
📈71Evaluate LLMs' cybersecurity risks and capabilities
-
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 35.4k • • 257 -
meta-llama/Prompt-Guard-86M
Text Classification • 0.3B • Updated • 23.4k • • 295 -
protectai/deberta-v3-base-prompt-injection-v2
Text Classification • 0.2B • Updated • 166k • • 82
Utils useful for LLM
-
Predict Memory
🧮102Calculate memory usage for model configurations
-
Model Memory Utility
🚀996Calculate vRAM needed for model training and inference
-
Transformers Timeline
🤗68Interactive timeline to explore the 🤗Transformers models
-
The Smol Training Playbook
📚2.83kThe secrets to building world-class LLMs
-
Agent Laboratory: Using LLM Agents as Research Assistants
Paper • 2501.04227 • Published • 95 -
Search-o1: Agentic Search-Enhanced Large Reasoning Models
Paper • 2501.05366 • Published • 102 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 109 -
Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments
Paper • 2501.10893 • Published • 26
-
Training Large Language Models to Reason in a Continuous Latent Space
Paper • 2412.06769 • Published • 92 -
Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
Paper • 2408.03314 • Published • 63 -
Evolving Deeper LLM Thinking
Paper • 2501.09891 • Published • 115 -
Kimi k1.5: Scaling Reinforcement Learning with LLMs
Paper • 2501.12599 • Published • 126