mradermacher/QRWKV6-7B-Base-GGUF
Same weights, converted vs recursal/QRWKV6-7B-Base. Same weights stored in another dtype (BF16 → F16/F32), plus 196 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/224, lm_head 0/1
Same weights, converted vs recursal/QRWKV6-7B-Base. Same weights stored in another dtype (BF16 → F16/F32), plus 196 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/224, lm_head 0/1