mradermacher/RLPR-Llama3.1-8B-Inst-GGUF

Same weights, converted vs openbmb/RLPR-Llama3.1-8B-Inst. Same weights stored in another dtype (BF16 → F16/F32), plus 1 new tensors.

Tensors changed: Attention 0/128, Norms 0/65, MLP 0/96, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse