mehuldamani/RLCR-hotpot-octo
Partial fine-tune vs OctoThinker/OctoThinker-8B-Short-Base. Partial change: 87% of the weights changed (attention, mlp, norms), in 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 13/65, MLP 96/96, Attention 128/128, lm_head 0/1
1 derivatives checked
- mradermacher/RLCR-hotpot-octo-GGUF: Same weights, converted