LiquidAI/LFM2.5-1.2B-JP
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
12 derivatives checked
- LiquidAI/LFM2.5-1.2B-JP-GGUF: Same weights, converted
- mradermacher/LFM2.5-1.2B-JP-i1-GGUF: Quantization
- LiquidAI/LFM2.5-1.2B-JP-MLX-4bit: Quantization
- DevQuasar/LiquidAI.LFM2.5-1.2B-JP-GGUF: Same weights, converted
- mradermacher/LFM2.5-1.2B-JP-GGUF: Same weights, converted
- LiquidAI/LFM2.5-1.2B-JP-MLX-8bit: Quantization
- LiquidAI/LFM2.5-1.2B-JP-MLX-5bit: Quantization
- LiquidAI/LFM2.5-1.2B-JP-MLX-6bit: Quantization
- LiquidAI/LFM2.5-1.2B-JP-MLX-bf16: Same weights, repacked
- tatsuyaaaaaaa/LFM2.5-1.2B-JP-gguf: Same weights, converted
- mmnga-o/LFM2.5-1.2B-JP-gguf: Quantization
- ryukin164/LFM2.5-1.2B-Q4-JP: Partial fine-tune