Blackroot/Mirai-3.0-70B
Full fine-tune vs Bllossom/llama-3-Korean-Bllossom-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
7 derivatives checked
- mradermacher/Mirai-3.0-70B-i1-GGUF: Quantization
- mradermacher/Mirai-3.0-70B-GGUF: Quantization
- KaraKaraWarehouse/Llama-MiraiFanfare-2-3.3-70B: Full fine-tune
- KaraKaraModel/Llama-3.X-Workout-70B: Full fine-tune
- KaraKaraWarehouse/Llama-ProgressPushDoll-3.3-70Bees: Full fine-tune
- Nohobby/L3.3-Prikol-70B-v0.1a: Full fine-tune
- KaraKaraWarehouse/oiiaioiiai-A: Full fine-tune