Raven-Pro/mixup1001
Partial fine-tune vs athirdpath/Theia-21B-v1_pretrained. Partial change: 43% of the weights changed (attention, embeddings, mlp), in 30 of 70 layers.
Tensors changed: Embeddings 1/1, Norms 0/141, MLP 90/210, Attention 120/280, lm_head 0/1
2 derivatives checked
- mradermacher/mixup1001-i1-GGUF: Quantization
- mradermacher/mixup1001-GGUF: Quantization