LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ToolBench-Full-SFT-1Epoch

Full fine-tune vs LiquidAI/LFM2.5-8B-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 14/60, Attention 24/24

2 derivatives checked

• LLM-OS-Models/LFM2.5-8B-A1B-Terminal-ToolBench-Full-SFT-1Epoch-GGUF: Same weights, converted
• LLM-OS-Models/Fabliq-8B-Agent: Full fine-tune

On the Hub · Downloads on Model Pulse