allura-org/remnant-mn-12b

Full fine-tune vs mistralai/Mistral-Nemo-Instruct-2407. Fine-tune: 99% of the weights changed, across 40 of 40 layers.

Tensors changed: Norms 30/81, MLP 120/120, Attention 157/160

3 derivatives checked

• bartowski/allura-org_remnant-mn-12b-GGUF: Same weights, converted
• mradermacher/remnant-mn-12b-i1-GGUF: Quantization
• mradermacher/remnant-mn-12b-GGUF: Quantization

On the Hub · Downloads on Model Pulse