Mihaiii/Metis-0.4

Full fine-tune vs Mihaiii/Metis-0.3. Fine-tune: 97% of the weights changed, across 32 of 32 layers.

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

4 derivatives checked

• TheBloke/Metis-0.4-GGUF: Quantization
• mradermacher/Metis-0.4-GGUF: Same weights, converted
• MaziyarPanahi/Metis-0.4-GGUF: Quantization
• mradermacher/Metis-0.4-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse