backyardai/Fimbulvetr-Holodeck-Erebus-Westlake-10.7B
Full fine-tune vs Sao10K/Fimbulvetr-11B-v2. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 97/97, MLP 144/144, Attention 192/192, lm_head 1/1
3 derivatives checked
- backyardai/Fimbulvetr-Holodeck-Erebus-Westlake-10.7B-GGUF: Quantization
- mradermacher/Fimbulvetr-Holodeck-Erebus-Westlake-10.7B-i1-GGUF: Quantization
- mradermacher/Fimbulvetr-Holodeck-Erebus-Westlake-10.7B-GGUF: Same weights, converted