kaptaan45/QaptaanLM-0.75B-Instruct

Partial fine-tune vs kaptaan45/QaptaanLM-0.75B. Partial change: 64% of the weights changed (attention, mlp, norms), in 24 of 24 layers.

Tensors changed: Embeddings 0/1, Norms 1/79, Attention 129/168, MLP 71/72

1 derivatives checked

• kaptaan45/QaptaanLM-0.75B-Instruct-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse