Sao10K/70B-L3.3-Cirrus-x1
Full fine-tune vs meta-llama/Llama-3.3-70B-Instruct. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
6 derivatives checked
- bartowski/70B-L3.3-Cirrus-x1-GGUF: Quantization
- mradermacher/70B-L3.3-Cirrus-x1-i1-GGUF: Quantization
- DevQuasar-12/Sao10K.70B-L3.3-Cirrus-x1-GGUF: Same weights, converted
- mradermacher/70B-L3.3-Cirrus-x1-GGUF: Quantization
- Jolly-Q/SOG_10k_70B: Full fine-tune
- Infermatic/R1-vortextic-70B-L3.3-v1: Full fine-tune