One-RL-to-See-Them-All/Orsta-32B-0321

Full fine-tune vs Qwen/Qwen2.5-VL-32B-Instruct. Fine-tune: 94% of the weights changed, across 64 of 64 layers.

Tensors changed: Attention 448/576, MLP 192/388, Norms 126/194, Embeddings 0/2, lm_head 1/1

1 derivatives checked

• mradermacher/Orsta-32B-0321-GGUF: Quantization (fewer layers)

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse