AI Briefing#ista-daslab
The latest AI and developer news about #ista-daslab, with the original source and a short summary.
The latest AI and developer news about #ista-daslab, with the original source and a short summary.
The expert-pruned build retains 98.7% of LiveCodeBench v6 performance while reducing transformer weights to 72.1 GB.
The new quantized models achieve near-BF16 performance at 3.50 bpw, while the expert-pruned Coder build reduces the resident working set to 29.6 GB.