LiquidAI/LFM2.5-Encoder-350M
Full fine-tune vs LiquidAI/LFM2.5-350M-Base. Fine-tune: 100% of the weights changed, across 16 of 16 layers.
Tensors changed: Embeddings 2/2, other 30/30, MLP 48/48, Norms 44/44, Attention 24/24
8 derivatives checked
- LiquidAI/d1-omni-600M: Full fine-tune (fewer layers)
- LiquidAI/LFM2.5-Encoder-350M-PII-Detector: Full fine-tune
- LiquidAI/LFM2.5-Encoder-350M-Prompt-Router: Full fine-tune
- LiquidAI/LFM2.5-Encoder-350M-Policy-Linter: Full fine-tune
- LiquidAI/LFM2.5-Encoder-350M-Diffusion: Full fine-tune
- LiquidAI/LFM2.5-Encoder-350M-GGUF: Not comparable yet
- LiquidAI/LFM2.5-Encoder-350M-Spellchecker: Full fine-tune
- Q1z/Pivot: Different architecture