mradermacher/LightGPT-0.5B-Qwen2-GGUF
Same weights, converted vs lightgpt/LightGPT-0.5B-Qwen2. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168
Same weights, converted vs lightgpt/LightGPT-0.5B-Qwen2. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168