bunnycore/Tulu-3.1-8B-SuperNova

Full fine-tune vs allenai/Llama-3.1-Tulu-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128

3 derivatives checked

• mradermacher/Tulu-3.1-8B-SuperNova-i1-GGUF: Quantization
• mradermacher/Tulu-3.1-8B-SuperNova-GGUF: Same weights, converted
• jaspionjader/Kosmos-EVAA-TSN-8B: Full fine-tune

On the Hub · Downloads on Model Pulse