DevQuasar-9/trashpanda-org.Llama3-24B-Mullein-v1-GGUF

Same weights, converted vs trashpanda-org/Llama3-24B-Mullein-v1. Same weights stored in another dtype (F16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/160, lm_head 0/1

On the Hub · Downloads on Model Pulse