matchaaaaa/Chaifighter-20B-v2.1
Full fine-tune (fewer layers) vs Sao10K/Fimbulvetr-11B-v2. Sao10K/Fimbulvetr-11B-v2 matches part of matchaaaaa/Chaifighter-20B-v2.1 (435 of its 795 tensors; the rest of matchaaaaa/Chaifighter-20B-v2.1 has no counterpart). On the shared part: 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
- mradermacher/Chaifighter-20B-v2.1-i1-GGUF: Quantization
- backyardai/Chaifighter-20B-v2.1-GGUF: Quantization
- mradermacher/Chaifighter-20B-v2.1-GGUF: Quantization