mradermacher/Nemotron-Research-Reasoning-Qwen-1.5B-Reasoning-Embedding-GGUF
Same weights, converted vs lucaswychan/Nemotron-Research-Reasoning-Qwen-1.5B-Reasoning-Embedding. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196