MaziyarPanahi/phi-2-logical-sft
Full fine-tune vs microsoft/phi-2. Fine-tune: 90% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 33/66, MLP 120/128, Attention 245/256, lm_head 2/2
3 derivatives checked
- MaziyarPanahi/phi-2-logical-sft-GGUF: Quantization
- mradermacher/phi-2-logical-sft-i1-GGUF: Quantization
- mradermacher/phi-2-logical-sft-GGUF: Same weights, converted