mradermacher/Flex-public-7B-1T-GGUF

Same weights, converted vs allenai/Flex-public-7B-1T. Same weights stored in another dtype (F32 → F16/F32).

Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/129, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse