PJMixers-Dev/Granite-3.1-Earthen-v0.3-1B-A400M

Partial fine-tune vs ibm-granite/granite-3.1-1b-a400m-instruct. Partial change: 6% of the weights changed (attention, other), in 24 of 24 layers.

Tensors changed: Embeddings 0/1, other 24/72, Norms 0/49, Attention 96/96

2 derivatives checked

On the Hub · Downloads on Model Pulse