NickupAI/LFM2.5-1.2B-Saiga-It-v2
Full fine-tune vs LiquidAI/LFM2.5-1.2B-Instruct. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 1/2, other 30/30, MLP 48/48, Norms 21/44, Attention 24/24
3 derivatives checked
- mradermacher/LFM2.5-1.2B-Saiga-It-v2-i1-GGUF: Quantization
- NickupAI/LFM2.5-1.2B-Saiga-It-v2-GGUF: Same weights, converted
- mradermacher/LFM2.5-1.2B-Saiga-It-v2-GGUF: Same weights, converted