invisietch/L3.3-Ignition-v0.1-70B
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: Norms 161/161, MLP 240/240, Attention 320/320
3 derivatives checked
- bartowski/invisietch_L3.3-Ignition-v0.1-70B-GGUF: Quantization
- mradermacher/L3.3-Ignition-v0.1-70B-i1-GGUF: Quantization
- mradermacher/L3.3-Ignition-v0.1-70B-GGUF: Quantization