mradermacher/granite-3.0-1b-a400m-base-GGUF

Same weights, converted vs ibm-granite/granite-3.0-1b-a400m-base. Same weights stored in another dtype (F32 → F16/F32), plus 48 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, other 0/48, Norms 0/49, Attention 0/96

On the Hub · Downloads on Model Pulse