Delta-Vector/Shimamura-70B

Full fine-tune vs zerofata/L3.3-GeneticLemonade-Unleashed-v3-70B. Fine-tune: 99% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320, lm_head 1/1

3 derivatives checked

• mradermacher/Shimamura-70B-i1-GGUF: Quantization
• mradermacher/Shimamura-70B-GGUF: Quantization
• ddh0/Cassiopeia-70B: Full fine-tune

On the Hub · Downloads on Model Pulse