OpenMMReasoner/OpenMMReasoner-RL

Full fine-tune vs Qwen/Qwen2.5-VL-7B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/2, Norms 57/122, MLP 280/280, Attention 324/324, lm_head 1/1

1 derivatives checked

• mradermacher/OpenMMReasoner-RL-GGUF: Same weights, converted (fewer layers)

On the Hub · Downloads on Model Pulse