yamatazen/Ayla-Light-12B-Stock
Full fine-tune vs yamatazen/Ayla-Light-12B. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 81/81, MLP 117/120, Attention 160/160
9 derivatives checked
- mradermacher/Ayla-Light-12B-Stock-i1-GGUF: Quantization
- mradermacher/Ayla-Light-12B-Stock-GGUF: Quantization
- DevQuasar-8/yamatazen.Ayla-Light-12B-Stock-GGUF: Same weights, converted
- MaziyarPanahi/Ayla-Light-12B-Stock-GGUF: Same weights, converted
- yamatazen/FlickeringLight-14B: Full fine-tune
- yamatazen/Ayla-Light-Extra-v2: Partial fine-tune (fewer layers)
- yamatazen/Ayla-Light-Extra: Same weights, repacked
- yamatazen/Iris-Light-12B: Full fine-tune
- yamatazen/Ayla-Light-16B: Partial fine-tune