InternRobotics/InternVLA-M1

Full fine-tune vs Qwen/Qwen2.5-VL-3B-Instruct. Fine-tune: 100% of the weights changed, across 36 of 36 layers.

Tensors changed: Embeddings 2/2, Norms 85/138, MLP 303/304, Attention 380/380

1 derivatives checked

• mradermacher/InternVLA-M1-GGUF: Same weights, converted (fewer layers)

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

On the Hub · Downloads on Model Pulse