Compressed Models V2
Collection
Compressed editions of Qwen3-14B (English, chat) with full MMLU-Pro reporting. E-AI Project. • 4 items • Updated
Atlas_EfficientAI
atlasium-efficient
AI & ML interests
Efficient Machine Learning, Pruning, Quantization, and Model Compression
Recent Activity
updated a collection 5 days ago
Compressed Models V2 updated a collection 5 days ago
Compressed Models V2 updated a collection 5 days ago
Compressed Models V2Organizations
updated a
collection 5 days ago
published 4
models 5 days ago
atlasium-efficient/Qwen3-10B-35pct-Compressed-14B-EN-V2
Text Generation • 10B • Updated • 284
atlasium-efficient/Qwen3-11B-30pct-Compressed-14B-EN-V2
Text Generation • 11B • Updated • 272
atlasium-efficient/Qwen3-11B-25pct-Compressed-14B-EN-V2
Text Generation • 11B • Updated • 279
atlasium-efficient/Qwen3-12B-20pct-Compressed-14B-EN-V2
Text Generation • 12B • Updated • 265
updated 4
models 5 days ago
atlasium-efficient/Qwen3-11B-30pct-Compressed-14B-EN-V2
Text Generation • 11B • Updated • 272
atlasium-efficient/Qwen3-11B-25pct-Compressed-14B-EN-V2
Text Generation • 11B • Updated • 279
atlasium-efficient/Qwen3-12B-20pct-Compressed-14B-EN-V2
Text Generation • 12B • Updated • 265
atlasium-efficient/Qwen3-10B-35pct-Compressed-14B-EN-V2
Text Generation • 10B • Updated • 284
updated 3
models 7 days ago
updated a
collection 8 days ago
published 2
models 8 days ago