JetBrains/Mellum-4b-dpo-all

Full fine-tune vs JetBrains/Mellum-4b-sft-all. Fine-tune: 100% of the weights changed, across 30 of 30 layers.

Tensors changed: Embeddings 1/1, Norms 3/61, MLP 90/90, Attention 120/120, lm_head 1/1

2 derivatives checked

• mradermacher/Mellum-4b-dpo-all-i1-GGUF: Quantization
• mradermacher/Mellum-4b-dpo-all-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse