mradermacher/LEM-Gemma3-1B-GGUF
Same weights, converted vs lthn/LEM-Gemma3-1B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/157, MLP 0/78, Attention 0/104
Same weights, converted vs lthn/LEM-Gemma3-1B. Same weights stored in another dtype (BF16 → F16/F32).
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/157, MLP 0/78, Attention 0/104