netcat420/MFANNv0.17.10

Partial fine-tune vs MaziyarPanahi/Llama-3-8B-Instruct-v0.4. Partial change: 46% of the weights changed (attention, mlp, norms), in 32 of 32 layers.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 8/65, MLP 40/96, Attention 128/128

3 derivatives checked

• mradermacher/MFANNv0.17.10-i1-GGUF: Quantization
• featherless-ai-quants/netcat420-MFANNv0.17.10-GGUF: Quantization
• mradermacher/MFANNv0.17.10-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse