ddh0/Cassiopeia-70B

Full fine-tune vs Delta-Vector/Shimamura-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/1, Norms 148/161, MLP 240/240, Attention 320/320, lm_head 1/1

3 derivatives checked

• bartowski/ddh0_Cassiopeia-70B-GGUF: Quantization
• mradermacher/Cassiopeia-70B-i1-GGUF: Quantization
• mradermacher/Cassiopeia-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse