SvalTek/SpicedTahsin

Full fine-tune vs Nitral-AI/Hathor_Tahsin-L3-8B-v0.85. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

1 derivatives checked

• mradermacher/SpicedTahsin-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse