PrimeIntellect/INTELLECT-3.1

Full fine-tune vs zai-org/GLM-4.5-Air-Base. Fine-tune: 100% of the weights changed, across 46 of 46 layers.

Tensors changed: Embeddings 1/1, Norms 93/93, MLP 2460/2505, Attention 322/322, lm_head 1/1

1 derivatives checked

• wimmmm/PrimeIntellect-INTELLECT-3.1-GGUF: Same weights, converted

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

On the Hub · Downloads on Model Pulse