LiquidAI/LFM2-2.6B-Transcript
Full fine-tune vs LiquidAI/LFM2-2.6B. Fine-tune: 100% of the weights changed, across 30 of 30 layers.
Tensors changed: Embeddings 2/2, other 66/66, MLP 90/90, Norms 76/76, Attention 32/32
5 derivatives checked
- LiquidAI/LFM2-2.6B-Transcript-GGUF: Same weights, converted
- DevQuasar/LiquidAI.LFM2-2.6B-Transcript-GGUF: Same weights, converted
- mradermacher/LFM2-2.6B-Transcript-i1-GGUF: Quantization
- mlx-community/LFM2-2.6B-Transcript-4bit: Quantization
- mradermacher/LFM2-2.6B-Transcript-GGUF: Same weights, converted