DevQuasar-8/Qwen.Qwen1.5-14B-GGUF
Same weights, converted vs Qwen/Qwen1.5-14B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/280, lm_head 0/1
Same weights, converted vs Qwen/Qwen1.5-14B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/81, MLP 0/120, Attention 0/280, lm_head 0/1