mradermacher/MiniPLM-Qwen-200M-GGUF
Same weights, converted vs MiniLLM/MiniPLM-Qwen-200M. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/84
Same weights, converted vs MiniLLM/MiniPLM-Qwen-200M. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/84