mrcuddle/Lexi-Lumimaid-Llama3.1-8B

Full fine-tune vs NeverSleep/Lumimaid-v0.2-8B. Fine-tune: 90% of the weights changed, across 31 of 31 layers.

Tensors changed: Embeddings 0/1, Norms 15/63, MLP 90/93, Attention 120/124, lm_head 1/1

2 derivatives checked

• mradermacher/Lexi-Lumimaid-Llama3.1-8B-i1-GGUF: Quantization
• mradermacher/Lexi-Lumimaid-Llama3.1-8B-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse