mradermacher/Llama3.1-elm-turbo-3B-instruct-GGUF

Same weights, converted vs slicexai/Llama3.1-elm-turbo-3B-instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/96, lm_head 0/1

On the Hub · Downloads on Model Pulse