Nexesenex/Llama_3.2_3b_Kermes_v2.1

Full fine-tune vs Nexesenex/Llama_3.2_3b_Kermes_0.20. Fine-tune: 100% of the weights changed, across 28 of 28 layers.

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

3 derivatives checked

• mradermacher/Llama_3.2_3b_Kermes_v2.1-i1-GGUF: Quantization
• mradermacher/Llama_3.2_3b_Kermes_v2.1-GGUF: Same weights, converted
• NexesQuants/Llama_3.2_3b_Kermes_v2.1-iMat-CQ-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse