mradermacher/Llama3B-GoEmotions_4bit-GGUF

Same weights, converted vs FritzStack/Llama3B-GoEmotions_4bit. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse