AyoubChLin/lfm2.5-2.6b-fable5-coding-agent
Full fine-tune vs LiquidAI/LFM2.5-2.6B. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 1/2, other 66/66, MLP 90/90, Norms 53/76, Attention 32/32
3 derivatives checked
- saidutta69/lfm2.5-2.6b-fable5-coding-agent-heretic: Abliterated
- ansulev/lfm2.5-2.6b-fable5-coding-agent-heretic: Abliterated
- AyoubChLin/LFM2.5-2.6B-fable5-coding-agent-GGUF: Same weights, converted