mehuldamani/RLVR-hotpot-octo

Full fine-tune vs OctoThinker/OctoThinker-8B-Short-Base. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 0/1

1 derivatives checked

• mradermacher/RLVR-hotpot-octo-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse