Nexesenex/Llama_3.2_3b_Kermes_v1

Full fine-tune vs NousResearch/Hermes-3-Llama-3.2-3B. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

Tensors changed: Embeddings 1/1, Norms 26/57, MLP 84/84, Attention 112/112

3 derivatives checked

• mradermacher/Llama_3.2_3b_Kermes_v1-i1-GGUF: Quantization
• mradermacher/Llama_3.2_3b_Kermes_0.1_bf16-GGUF: Same weights, converted
• mradermacher/Llama_3.2_3b_Kermes_v1-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse