TareksLab/Mithril-Prose-LLaMa-70B

Full fine-tune vs ArliAI/DS-R1-Distill-70B-ArliAI-RpR-v4-Large. Fine-tune: 100% of the weights changed, across 80 of 80 layers.

Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1

1 derivatives checked

• mradermacher/Mithril-Prose-LLaMa-70B-GGUF: Quantization

On the Hub · Downloads on Model Pulse