stornic56/Spark-X2.5-1.7B-GGUF
Same weights, converted vs XHToken/Spark-X2.5-1.7B. Same weights stored in another dtype (BF16 → BF16/F32), plus 28 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/56
Same weights, converted vs XHToken/Spark-X2.5-1.7B. Same weights stored in another dtype (BF16 → BF16/F32), plus 28 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/56