LiquidAI/LFM2.5-Encoder-230M
Full fine-tune vs LiquidAI/LFM2.5-230M-Base. Fine-tune: 100% of the weights changed, across 14 of 14 layers.
Tensors changed: Embeddings 2/2, other 24/24, MLP 42/42, Norms 40/40, Attention 24/24
2 derivatives checked
- LiquidAI/LFM2.5-Encoder-230M-GGUF: Not comparable yet
- cstr/LFM2.5-Encoder-230M-GGUF: Not comparable yet
1 other repos hold byte-for-byte identical weight files.