NousResearch/Hermes-2-Pro-Llama-3-8B
Full fine-tune vs NousResearch/Meta-Llama-3-8B. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 63/65, MLP 96/96, Attention 128/128
30 derivatives checked
- NousResearch/Hermes-2-Theta-Llama-3-8B: Full fine-tune
- vicgalle/Configurable-Hermes-2-Pro-Llama-3-8B: LoRA-style
- bartowski/Hermes-2-Theta-Llama-3-8B-GGUF: Full fine-tune
- thesven/Hermes-2-Theta-Llama-3-8B-GGUF: Full fine-tune
- NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF: Full fine-tune
- QuantFactory/Hermes-2-Pro-Llama-3-8B-GGUF: Quantization
- second-state/Hermes-2-Pro-Llama-3-8B-GGUF: Same weights, converted
- qwp4w3hyb/Hermes-2-Pro-Llama-3-8B-iMat-GGUF: Same weights, converted
- LiteLLMs/Hermes-2-Theta-Llama-3-8B-GGUF: Full fine-tune
- adamksn/Hermes-2-Theta-Llama-3-8B-32k-GGUF: Full fine-tune
- solidrust/Hermes-2-Pro-Llama-3-8B-AWQ: Quantization
- gutsartificial/hermes-2-pro-llama3-entity-mapping-gguf-f16: LoRA-style
- lik07/Hermes-Sthero-v1: Full fine-tune
- OpenPipe/Hermes-2-Theta-Llama-3-8B-32k: Full fine-tune
- lighteternal/Llama3-merge-biomed-8b: Full fine-tune
- kevinkawchak/NousResearch-Hermes-2-Pro-Llama-3-8B-Molecule16: LoRA-style
- Jebadiah/hermes-SOVL-stone-l3-8b: Full fine-tune
- mergekit-community/Hermes-2-Pro-Llama-3-13B: Partial fine-tune (fewer layers)
- kaizuberbuehler/Alpesteibock-Llama-3-8B-Alpha: LoRA-style
- Jebadiah/hermes-Lexi-fun-stone-l3-8b: Full fine-tune
- Jebadiah/hermes-lewdPlay-stone-l3-8b: Full fine-tune
- mergekit-community/Llama3-12B-wwe: Full fine-tune (fewer layers)
- picAIso/TARS-8B-llama-REMIX-v2: Full fine-tune
- Jebadiah/dolphin-hermes-stone-l3-8b-1m: Partial fine-tune
- mergekit-community/mergekit-passthrough-dmirwnd: Full fine-tune (fewer layers)
- mrcuddle/Bagel-Hermes-2-Pro-Llama3-8B: Full fine-tune
- mergekit-community/Llama-3-8B-666: Full fine-tune (fewer layers)
- mergekit-community/Llama3-13B-ku: Different architecture
- picAIso/TARS-8B-llama-REMIX: Full fine-tune
- picAIso/TARS-8B-llama-TIEMIX: Full fine-tune
6 other repos hold byte-for-byte identical weight files.