Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
• 17
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Quantization-Aware Healing: A Practical Recipe for Recovering Compressed, 4-Bit LLMs
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Articles
MultiverseComputingCAI/LittleLamb
Text Generation • 0.3B • Updated • 1.11k • 10
MultiverseComputingCAI/Hypernova-60B-2605
Text Generation • 59B • Updated • 3.94k • 16
MultiverseComputingCAI/Hypernova-60B-2602
Text Generation • 59B • Updated • 360 • 15
MultiverseComputingCAI/Pulsar-16B-NVFP4
9B • Updated • 73 • 3
MultiverseComputingCAI/Pulsar-16B-BF16
16B • Updated • 3.2k • 4
MultiverseComputingCAI/Pulsar-16B-FP8
16B • Updated • 8 • 3
MultiverseComputingCAI/HyperNova-60B
Text Generation • 60B • Updated • 533 • 61
MultiverseComputingCAI/Hypernova-60B-2602-GGUF
Text Generation • 59B • Updated • 62 • 6
MultiverseComputingCAI/LittleLamb-ToolCalling
Text Generation • 0.3B • Updated • 439 • 3
MultiverseComputingCAI/Qwen3-Next-80B-A3B-Thinking-Uncensored
Text Generation • 80B • Updated • 87 • 16