yentinglin/Llama-3-Taiwan-70B-Instruct
Full fine-tune vs meta-llama/Meta-Llama-3-70B. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 1/1, Norms 161/161, MLP 240/240, Attention 320/320, lm_head 1/1
6 derivatives checked
- gaianet/Llama-3-Taiwan-70B-Instruct-GGUF: Same weights, converted
- mradermacher/Llama-3-Taiwan-70B-Instruct-i1-GGUF: Quantization
- second-state/Llama-3-Taiwan-70B-Instruct-GGUF: Same weights, converted
- chienweichang/Llama-3-Taiwan-70B-Instruct-GGUF: Same weights, converted
- featherless-ai-quants/yentinglin-Llama-3-Taiwan-70B-Instruct-GGUF: Quantization
- mradermacher/Llama-3-Taiwan-70B-Instruct-GGUF: Quantization