allenai/Olmo-3.1-7B-RL-Zero-Math

Full fine-tune vs allenai/Olmo-3-1025-7B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, MLP 96/96, Norms 128/129, Attention 128/128, lm_head 1/1

2 derivatives checked

• mradermacher/Olmo-3.1-7B-RL-Zero-Math-GGUF: Same weights, converted
• mradermacher/Olmo-3.1-7B-RL-Zero-Math-i1-GGUF: Quantization

On the Hub · Downloads on Model Pulse