MathLLMs/MathCoder-VL-8B

Full fine-tune vs OpenGVLab/InternVL2-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Attention 160/160, Norms 161/161, MLP 198/198, Embeddings 4/4, other 48/48

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

On the Hub · Downloads on Model Pulse