smelborp/StellarDong-72b

Full fine-tune vs anthracite-org/magnum-v1-72b. Fine-tune: 98% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 0/1, Norms 129/161, MLP 240/240, Attention 560/560, lm_head 1/1

2 derivatives checked

• mradermacher/StellarDong-72b-i1-GGUF: Quantization
• mradermacher/StellarDong-72b-GGUF: Quantization

On the Hub · Downloads on Model Pulse