Yobenboben/L3.3-ElectraEXTRA-R1-70b
Partial fine-tune vs Nohobby/L3.3-Prikol-70B-EXTRA. Partial change: 84% of the weights changed (attention, lm_head, mlp, norms), in 80 of 80 layers.
Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 72/161, MLP 196/240, Attention 310/320
2 derivatives checked
- mradermacher/L3.3-ElectraEXTRA-R1-70b-i1-GGUF: Quantization
- mradermacher/L3.3-ElectraEXTRA-R1-70b-GGUF: Quantization