Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.2

Full fine-tune vs artificialguybr/LLAMA-3.2-1B-OpenHermes2.5. Fine-tune: 97% of the weights changed, across 16 of 16 layers.

Tensors changed: lm_head 1/1, Norms 28/33, MLP 47/48, Attention 58/64

2 derivatives checked

• mradermacher/Llama_3.2_1b_Odyssea_Escalation_0.2-GGUF: Same weights, converted
• Nexesenex/Llama_3.2_1b_Odyssea_Escalation_0.4: Full fine-tune

On the Hub · Downloads on Model Pulse