saishf/SOVLish-Maid-L3-8B

Partial fine-tune vs NeverSleep/Llama-3-Lumimaid-8B-v0.1-OAS. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

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

2 derivatives checked

• mradermacher/SOVLish-Maid-L3-8B-GGUF: Same weights, converted
• featherless-ai-quants/saishf-SOVLish-Maid-L3-8B-GGUF: Quantization

On the Hub · Downloads on Model Pulse