NickupAI/LFM2.5-1.2B-Saiga-It-v3

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-v3-i1-GGUF: Quantization
• mradermacher/LFM2.5-1.2B-Saiga-It-v3-GGUF: Same weights, converted
• NickupAI/LFM2.5-1.2B-Saiga-It-v3-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse