evalengine/unbound-q-0.8b-GGUF
Same weights, converted vs evalengine/unbound-q-0.8b. Same weights stored in another dtype (BF16 → BF16/F32), plus 18 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24
Same weights, converted vs evalengine/unbound-q-0.8b. Same weights stored in another dtype (BF16 → BF16/F32), plus 18 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24