sophosympatheia/Sophos-eva-euryale-v1.0
Full fine-tune vs EVA-UNIT-01/EVA-LLaMA-3.33-70B-v0.0. Fine-tune: 99% of the weights changed, across 80 of 80 layers.
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 240/240, Attention 320/320, lm_head 1/1
5 derivatives checked
- featherless-ai-quants/sophosympatheia-Sophos-eva-euryale-v1.0-GGUF: Quantization
- mradermacher/Evayale-v1.0-i1-GGUF: Quantization
- mradermacher/Sophos-eva-euryale-v1.0-i1-GGUF: Quantization
- mradermacher/Evayale-v1.0-GGUF: Quantization
- mradermacher/Sophos-eva-euryale-v1.0-GGUF: Quantization