Jamphus/LongWriter-glm4-9b-abliterated

Partial fine-tune vs zai-org/LongWriter-glm4-9b. Partial change: 11% of the weights changed (attention, embeddings, mlp), in 8 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 0/81, MLP 6/80, Attention 3/120, other 0/2

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

On the Hub · Downloads on Model Pulse