KaraKaraWarehouse/Llama-MiraiFanfare-2-3.3-70B

Full fine-tune vs Blackroot/Mirai-3.0-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: lm_head 1/1, Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320

3 derivatives checked

• mradermacher/Llama-MiraiFanfare-2-3.3-70B-i1-GGUF: Quantization
• featherless-ai-quants/KaraKaraWitch-Llama-MiraiFanfare-2-3.3-70B-GGUF: Quantization
• mradermacher/Llama-MiraiFanfare-2-3.3-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse