Nexusflow/Athene-V2-Chat
Full fine-tune vs Qwen/Qwen2.5-72B-Instruct. Fine-tune: 98% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 112/161, MLP 240/240, Attention 559/560, lm_head 1/1
7 derivatives checked
- bartowski/Athene-V2-Chat-GGUF: Quantization
- mradermacher/Athene-V2-Chat-i1-GGUF: Quantization
- featherless-ai-quants/Nexusflow-Athene-V2-Chat-GGUF: Quantization
- mradermacher/Athene-V2-Chat-GGUF: Quantization
- DevQuasar-5/Nexusflow.Athene-V2-Chat-GGUF: Quantization
- lmstudio-community/Athene-V2-Chat-GGUF: Quantization
- Nohobby/Q2.5-Atess-72B: Full fine-tune