cloudversia/Cloudversia-Thor-7B

Full fine-tune vs OpenPipe/mistral-ft-optimized-1218. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 22/65, MLP 93/96, Attention 124/128, lm_head 1/1

1 derivatives checked

• mradermacher/Cloudversia-Thor-7B-GGUF: Same weights, converted

47 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse