mradermacher/WARD-0.8b-GGUF
Same weights, converted vs tricao1105/WARD-0.8b. Same weights stored in another dtype (BF16 → F16/F32), plus 19 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24
Same weights, converted vs tricao1105/WARD-0.8b. Same weights stored in another dtype (BF16 → F16/F32), plus 19 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24