LiquidAI/LFM2-350M-ENJP-MT
Full fine-tune vs LiquidAI/LFM2-350M. 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/LFM2-350M-ENJP-MT-GGUF: Same weights, converted
- mradermacher/LFM2-350M-ENJP-MT-GGUF: Same weights, converted
- shisa-ai/shisa-v2.1c-lfm2-350m: Full fine-tune
- shisa-ai/shisa-v2.1c-lfm2-350m-sft3: Full fine-tune