gyung/LFM2-8B-Terminal-SFT-Unsloth

Full fine-tune vs LiquidAI/LFM2-8B-A1B. Fine-tune: 100% of the weights changed, across 24 of 24 layers.

Tensors changed: MLP 2140/2162, Embeddings 1/2, other 54/54, Norms 16/60, Attention 24/24

2 derivatives checked

• mradermacher/LFM2-8B-Terminal-SFT-Unsloth-i1-GGUF: Quantization
• mradermacher/LFM2-8B-Terminal-SFT-Unsloth-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse