sirev/LFM2-2.6B-Uncensored-X64
Full fine-tune vs LiquidAI/LFM2-2.6B. Fine-tune: 95% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 0/2, other 44/66, MLP 90/90, Norms 0/76, Attention 32/32
3 derivatives checked
- mradermacher/LFM2-2.6B-Uncensored-X64-i1-GGUF: Quantization
- mradermacher/LFM2-2.6B-Uncensored-X64-GGUF: Same weights, converted
- sirev/LFM2-2.6B-Uncensored-X64-Q4_K_M-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.