Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
• 6
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Articles
Organization Card
Multiverse Computing
Multiverse Computing is a global leader in providing efficient AI models and systems, universalizing impactful and affordable AI across the cloud, on-prem, and at the edge.
Check out our new model: https://huggingface.co/MultiverseComputingCAI/Hypernova-60B-2602
Website: https://multiversecomputing.com
Discord: https://discord.gg/6sCqREAu
Github: http://github.com/CompactifAI
models 10
MultiverseComputingCAI/LittleLamb
Text Generation • 0.3B • Updated • 703 • 11
MultiverseComputingCAI/Hypernova-60B-2605
Text Generation • 59B • Updated • 5.4k • 21
MultiverseComputingCAI/Hypernova-60B-2602
Text Generation • 59B • Updated • 223 • 15
MultiverseComputingCAI/Pulsar-16B-NVFP4
9B • Updated • 143 • 3
MultiverseComputingCAI/Pulsar-16B-BF16
16B • Updated • 1.07k • 4
MultiverseComputingCAI/Pulsar-16B-FP8
16B • Updated • 20 • 3
MultiverseComputingCAI/HyperNova-60B
Text Generation • 60B • Updated • 276 • 62
MultiverseComputingCAI/Hypernova-60B-2602-GGUF
Text Generation • 59B • Updated • 68 • 6
MultiverseComputingCAI/LittleLamb-ToolCalling
Text Generation • 0.3B • Updated • 472 • 3
MultiverseComputingCAI/Qwen3-Next-80B-A3B-Thinking-Uncensored
Text Generation • 80B • Updated • 72 • 16