mradermacher/stablelm-base-alpha-7b-sharded-GGUF

Same weights, converted vs ethzanalytics/stablelm-base-alpha-7b-sharded. Same weights stored in another dtype (F32/BOOL → F16/F32).

Tensors changed: Embeddings 0/2, Attention 0/32, Norms 0/66, MLP 0/64

On the Hub · Downloads on Model Pulse