My series of fully open, state-of-the-art small mixture-of-experts models.
🔄 In a Training Loop
aquilesfd
aquilesfd
AI & ML interests
research
Recent Activity
liked a model about 2 hours ago
internlm/Sage-S2.1-Flash repliedto Banaxi-Tech's post 2 days ago
We're introducing KV1 1.2B.
Its our first KV1 model using a 2 bit KV cache, based on LFM 2.5 1.2B.
KV1 1.2B retains 75.8% of original intelligence.
More details: https://huggingface.co/spaces/klein-ml/blog#kv1-1.2b
Model https://huggingface.co/klein-ml/KV1-1.2B
liked a model 2 days ago
Cactus-Compute/mirage