reaperdoesntknow/LFM2.5-8B-A1B-Opus-Distil

Partial fine-tune vs LiquidAI/LFM2.5-8B-A1B. Partial change: 1% of the weights changed (attention, norms, other), in 8 of 24 layers.

Tensors changed: MLP 0/2162, Embeddings 0/2, other 12/54, Norms 4/60, Attention 8/24

2 derivatives checked

• DarkKitsune/LFM2.5-8B-A1B-Opus-Distil-Q5_K_M-imat-GGUF: Quantization
• Tivaphraen/LFM2.5-8B-A1B-Opus-Distil-GGUF: Quantization

On the Hub · Downloads on Model Pulse