Nexesenex/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02
Full fine-tune vs dphn/dolphin-2.9.1-llama-3-70b. Fine-tune: 100% of the weights changed, across 80 of 80 layers.
Tensors changed: Norms 161/161, MLP 240/240, Attention 320/320
7 derivatives checked
- mradermacher/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02-i1-GGUF: Quantization
- mradermacher/Llama_3.x_70b_L3.3_Dolphin_128K_v1.02-GGUF: Quantization
- Nexesenex/Llama_3.x_70b_Nemdohertess_v2.0: Full fine-tune
- Nexesenex/Llama_3.x_70b_Dolmen_v1.2: Full fine-tune
- Nexesenex/Llama_3.x_70b_SmarTrident_v1.02: Full fine-tune
- NexesMess/Llama_3.x_70b_Dolmen_v1.0: Full fine-tune
- Nexesenex/Llama_3.x_70b_Kraken_v1.1: Full fine-tune