liminerity/binarized-ingotrix-slerp-7b
Full fine-tune vs eren23/dpo-binarized-NeuralTrix-7B. Fine-tune: 97% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 93/96, Attention 124/128, lm_head 1/1
2 derivatives checked
- mradermacher/binarized-ingotrix-slerp-7b-i1-GGUF: Quantization
- mradermacher/binarized-ingotrix-slerp-7b-GGUF: Same weights, converted