Yvthyvq/Liujgoj-Cantonese-Qwen3-8B-Base
Same weights, repacked vs Qwen/Qwen3-8B-Base. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Norms 0/145, MLP 0/108, Attention 0/144
5 derivatives checked
- mradermacher/liujgoj-v1-qwen3-8b-base-i1-GGUF: Quantization
- mradermacher/Liujgoj-Cantonese-Qwen3-8B-Base-i1-GGUF: Quantization
- mradermacher/Liujgoj-Cantonese-Qwen3-8B-Base-GGUF: Same weights, converted
- mradermacher/liujgoj-v1-qwen3-8b-base-GGUF: LoRA-style
- Yvthyvq/Liujgoj-Cantonese-Qwen3-8B-Instruct: LoRA-style