djuna/L3.1-RPGramMax-2.5

Full fine-tune vs ArliAI/Llama-3.1-8B-ArliAI-RPMax-v1.1. Fine-tune: 91% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, Norms 33/65, MLP 93/96, Attention 124/128, lm_head 1/1

2 derivatives checked

• mradermacher/L3.1-RPGramMax-2.5-i1-GGUF: Quantization
• mradermacher/L3.1-RPGramMax-2.5-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse