KaraKaraWarehouse/L3.1-70b-Inori

Full fine-tune vs Fizzarolli/L3.1-70b-glitz-v0.2. 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

3 derivatives checked

• mradermacher/L3.1-70b-Inori-i1-GGUF: Quantization
• mradermacher/L3.1-70b-Inori-GGUF: Quantization
• featherless-ai-quants/KaraKaraWitch-L3.1-70b-Inori-GGUF: Quantization

On the Hub · Downloads on Model Pulse