Haleshot/Mathmate-7B-DELLA

Full fine-tune vs AI-MO/NuminaMath-7B-TIR. Fine-tune: 100% of the weights changed, across 30 of 30 layers.

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

1 derivatives checked

• mradermacher/Mathmate-7B-DELLA-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse