mradermacher/Qwen2.5-1.5B-Instruct-Thai-SFT-GGUF
Same weights, converted vs jaeyong2/Qwen2.5-1.5B-Instruct-Thai-SFT. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196
Same weights, converted vs jaeyong2/Qwen2.5-1.5B-Instruct-Thai-SFT. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/57, MLP 0/84, Attention 0/196