mradermacher/SFT-TLDR-Qwen2-0.5B-SMALL-GGUF
Same weights, converted vs rlhf-and-friends/TLDR-Qwen2-0.5B-SmallSFT. 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 rlhf-and-friends/TLDR-Qwen2-0.5B-SmallSFT. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/72, Attention 0/168