LiquidAI/LFM2.5-1.2B-JP-202606
Full fine-tune vs LiquidAI/LFM2.5-1.2B-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
10 derivatives checked
- LiquidAI/LFM2.5-1.2B-JP-202606-GGUF: Same weights, converted
- woolisbest2026/LFM2.5-1.2B-JP-202606-GGUF: Same weights, converted
- LiquidAI/LFM2.5-1.2B-JP-202606-MLX-4bit: Quantization
- LiquidAI/LFM2.5-1.2B-JP-202606-MLX-8bit: Quantization
- LiquidAI/LFM2.5-1.2B-JP-202606-MLX-6bit: Quantization
- LiquidAI/LFM2.5-1.2B-JP-202606-MLX-5bit: Quantization
- fukayatti0/jev-japanese-judgment: Not comparable yet
- akiFQC/LFM2.5-1.2B-JP-202606-Conf-Extract: LoRA-style
- TeamDelta/LFM-2.5-1.2B-Novel-JP: LoRA-style
- CloudGoat/LFM2.5-1.2B-FusionJP: Full fine-tune