mradermacher/ADAPT-Qwen3-8.5B-GGUF
Same weights, converted vs Harvard-DCML/ADAPT-Qwen3-8.5B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/85, MLP 0/63, Attention 0/84, lm_head 0/1
Same weights, converted vs Harvard-DCML/ADAPT-Qwen3-8.5B. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/85, MLP 0/63, Attention 0/84, lm_head 0/1