MLP-KTLim/llama-3-Korean-Bllossom-8B
Full fine-tune vs meta-llama/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 1/1, Norms 65/65, MLP 96/96, Attention 128/128, lm_head 1/1
8 derivatives checked
- mradermacher/llama-3-Korean-Bllossom-8B-GGUF: Same weights, converted
- MLP-KTLim/llama-3-Korean-Bllossom-8B-gguf-Q4_K_M: Quantization
- featherless-ai-quants/MLP-KTLim-llama-3-Korean-Bllossom-8B-GGUF: Quantization
- joongi007/llama-3-Korean-Bllossom-8B-20240809-GGUF: Full fine-tune
- grimjim/llama-3-Nephilim-v2.1-8B: Full fine-tune
- yongtaek-lim/pogny: Identical copy
- Gunulhona/Hermes-Llama-Merge: Full fine-tune
- carefood/agent1-health-analysis-8b: LoRA-style
3 other repos hold byte-for-byte identical weight files.