FourOhFour/Magic_v2_8B

Full fine-tune vs Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatML. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 39/81, MLP 120/120, Attention 160/160, lm_head 1/1

3 derivatives checked

• QuantFactory/Fatgirl_v2_8B-GGUF: Full fine-tune
• mradermacher/Magic_v2_8B-GGUF: Same weights, converted
• FourOhFour/Fatgirl_v2_8B: Full fine-tune

On the Hub · Downloads on Model Pulse