mradermacher/RLPR-Qwen2.5-7B-Base-GGUF
Same weights, converted vs RLAIF-V/RLPR-Qwen2.5-7B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/196, Norms 0/57, MLP 0/84, lm_head 0/1, Embeddings 0/1
Same weights, converted vs RLAIF-V/RLPR-Qwen2.5-7B-Base. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Attention 0/196, Norms 0/57, MLP 0/84, lm_head 0/1, Embeddings 0/1