OpenPipe/Hermes-2-Theta-Llama-3-8B-32k
Full fine-tune vs NousResearch/Hermes-2-Pro-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 65/65, MLP 96/96, Attention 128/128
4 derivatives checked
- mradermacher/Hermes-2-Theta-Llama-3-8B-32k-i1-GGUF: Quantization
- mradermacher/Hermes-2-Theta-Llama-3-8B-32k-GGUF: Same weights, converted
- featherless-ai-quants/OpenPipe-Hermes-2-Theta-Llama-3-8B-32k-GGUF: Quantization
- Babsie/ThetaBlackGorgon-8B: Full fine-tune
42 other repos hold byte-for-byte identical weight files.