LiquidAI/LFM2.5-Embedding-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
4 derivatives checked
- LiquidAI/LFM2.5-Embedding-350M-GGUF: Same weights, converted
- cstr/lfm2-embed-GGUF: Not comparable yet
- mradermacher/LFM2.5-Embedding-350M-GGUF: Same weights, converted
- mlx-community/LFM2.5-Embedding-350M-bf16: Same weights, repacked
1 other repos hold byte-for-byte identical weight files.