birgermoell/oellm-9b-math-rlvr-phase-a-32step-experimental

Partial fine-tune vs birgermoell/oellm-9b-math-rlvr-canary-step16-experimental. Partial change: 88% of the weights changed (attention, lm_head, mlp, norms), in 36 of 36 layers.

Tensors changed: lm_head 1/1, Embeddings 0/1, Norms 58/145, MLP 108/108, Attention 144/144

On the Hub · Downloads on Model Pulse