DavidAU/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B
Partial fine-tune vs NousResearch/DeepHermes-3-Llama-3-8B-Preview. Partial change: 71% of the weights changed (attention, mlp, norms), in 26 of 32 layers.
Tensors changed: Embeddings 0/1, Norms 52/65, MLP 78/96, Attention 104/128, lm_head 0/1
4 derivatives checked
- DevQuasar-13/DavidAU.L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF: Same weights, converted
- mradermacher/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-GGUF: Same weights, converted
- mradermacher/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-i1-GGUF: Quantization
- fairy322/L3.1-Dark-Reasoning-LewdPlay-evo-Hermes-R1-Uncensored-8B-i1-GGUF: Quantization
3 other repos hold byte-for-byte identical weight files.