mradermacher/RYS-Llama-3.1-8B-Instruct-GGUF

Same weights, converted vs dnhkng/RYS-Llama-3.1-8B-Instruct. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Norms 0/71, MLP 0/105, Attention 0/140, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse