Bllossom/llama-3-Korean-Bllossom-70B
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
11 derivatives checked
- mradermacher/llama-3-Korean-Bllossom-70B-i1-GGUF: Quantization
- featherless-ai-quants/Bllossom-llama-3-Korean-Bllossom-70B-GGUF: Quantization
- DevQuasar-10/Bllossom.llama-3-Korean-Bllossom-70B-GGUF: Same weights, converted
- mradermacher/llama-3-Korean-Bllossom-70B-GGUF: Quantization
- Blackroot/Mirai-3.0-70B: Full fine-tune
- KaraKaraWarehouse/BlenderCartel-llama33-70B-Pt2: Full fine-tune
- Blackroot/Mirai-70B-1.0: Full fine-tune
- Blackroot/Mirai-70B-0.2: Full fine-tune
- Blackroot/Mirai-70B-0.3: Full fine-tune
- Blackroot/Mirai-70B-2.1: Full fine-tune
- Blackroot/Mirai-70B-2: Full fine-tune