NousResearch/DeepHermes-3-Llama-3-8B-Preview
Full fine-tune vs meta-llama/Llama-3.1-8B. Fine-tune: 93% of the weights changed, across 32 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 64/65, MLP 96/96, Attention 128/128, lm_head 1/1
15 derivatives checked
- bartowski/NousResearch_DeepHermes-3-Llama-3-8B-Preview-GGUF: Quantization
- mradermacher/DeepHermes-3-Llama-3-8B-Preview-i1-GGUF: Quantization
- second-state/DeepHermes-3-Llama-3-8B-Preview-GGUF: Same weights, converted
- mradermacher/DeepHermes-3-Llama-3-8B-Preview-GGUF: Same weights, converted
- brittlewis12/DeepHermes-3-Llama-3-8B-Preview-GGUF: Same weights, converted
- DavidAU/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B: Partial fine-tune
- DevQuasar/NousResearch.DeepHermes-3-Llama-3-8B-Preview-GGUF: Same weights, converted
- gaianet/DeepHermes-3-Llama-3-8B-Preview-GGUF: Same weights, converted
- DavidAU/L3.1-Dark-Reasoning-Unholy-Hermes-R1-Uncensored-8B: Partial fine-tune
- Nexesenex/Llama_3.1_8b_Hermedive_R1_V1.01: Full fine-tune
- olaverse/MIST-Mini-8B: Full fine-tune
- Nexesenex/Llama_3.1_8b_Dolermed_R1_V1.01: Full fine-tune
- Yingyaeliae/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-heretic: Partial fine-tune
- mergekit-community/uncensored-mix: Abliterated
- mergekit-community/censored-mix: Full fine-tune