Tuwhy/Olmo-3-7B-Think-OPSA

Full fine-tune vs allenai/Olmo-3-7B-Think. Fine-tune: 94% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 0/1, MLP 96/96, Norms 127/129, Attention 128/128, lm_head 1/1

2 derivatives checked

• mradermacher/Olmo-3-7B-Think-OPSA-i1-GGUF: Quantization
• mradermacher/Olmo-3-7B-Think-OPSA-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse