tklohj/WindyFloLLM
Full fine-tune vs garage-bAInd/Platypus2-13B. Fine-tune: 98% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 1/1, Norms 29/81, MLP 117/120, Attention 156/160, lm_head 1/1
2 derivatives checked
- mradermacher/WindyFloLLM-GGUF: Quantization
- featherless-ai-quants/tklohj-WindyFloLLM-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.