ZeroXClem/L3SAO-Mix-SuperHermes-NovaPurosani-8B

Full fine-tune vs ZeroXClem/Llama3.1-Hermes3-SuperNova-8B-L3.1-Purosani-2-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

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

2 derivatives checked

• mradermacher/L3SAO-Mix-SuperHermes-NovaPurosani-8B-GGUF: Same weights, converted
• ZeroXClem/Llama-3.1-8B-SuperNova-EtherealHermes: Full fine-tune

On the Hub · Downloads on Model Pulse