darrellbest/Hemmingway-1-Heretic
Partial fine-tune vs Altworld/Hemmingway-1. Partial change: 14% of the weights changed (attention, mlp, norms), in 31 of 64 layers.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 3/209, Attention 30/448, MLP 33/192
6 derivatives checked
- mradermacher/Hemmingway-1-Heretic-i1-GGUF: Quantization
- mradermacher/Hemmingway-1-Heretic-GGUF: Quantization
- darrellbest/Hemmingway-1-Heretic-GGUF: Same weights, converted
- darrellbest/Hemmingway-1-Heretic-NVFP4: Quantization
- darrellbest/Hemmingway-1-Heretic-Text: Partial fine-tune
- darrellbest/Hemmingway-1-Heretic-FP8: Quantization