shenzhi-wang/Llama3-8B-Chinese-Chat
Full fine-tune vs meta-llama/Meta-Llama-3-8B-Instruct. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 15/65, MLP 96/96, Attention 128/128, lm_head 1/1
5 derivatives checked
- QuantFactory/Llama3-8B-Chinese-Chat-GGUF: Full fine-tune
- featherless-ai-quants/shenzhi-wang-Llama3-8B-Chinese-Chat-GGUF: Quantization
- mradermacher/Llama3-8B-Chinese-Chat-GGUF: Same weights, converted
- second-state/Llama3-8B-Chinese-Chat-GGUF: Full fine-tune
- DhruvalLabs/Llama3-8B-Chinese-Chat-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.