mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-i1-GGUF
Quantization vs chencindy/TinyStories-LLaMA2-20M-256h-4l-GQA. mradermacher/TinyStories-LLaMA2-20M-256h-4l-GQA-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 9 tensors match exactly and 30 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/9, MLP 0/12, Attention 0/16