teknium/OpenHermes-2.5-Mistral-7B
Full fine-tune vs mistralai/Mistral-7B-v0.1. Fine-tune: 100% of the weights changed, across 32 of 32 layers.
Tensors changed: Norms 17/65, MLP 96/96, Attention 128/128
30 derivatives checked
- TheBloke/OpenHermes-2.5-Mistral-7B-GGUF: Quantization
- TheBloke/OpenHermes-2.5-Mistral-7B-AWQ: Quantization
- sayhan/OpenHermes-2.5-Strix-Philosophy-Mistral-7B-LoRA: LoRA-style
- TheBloke/OpenHermes-2.5-Mistral-7B-GPTQ: Quantization
- second-state/OpenHermes-2.5-Mistral-7B-GGUF: Quantization
- QuantFactory/OpenHermes-2.5-Mistral-7B-GGUF: Quantization
- Mungert/Prox-MistralHermes-7B-GGUF: Full fine-tune
- MaziyarPanahi/OpenHermes-2.5-Mistral-7B-GGUF: Quantization
- mradermacher/OpenHermes-2.5-Mistral-7B-GGUF: Same weights, converted
- adamksn/NeuralHermes-2.5-Mistral-7B-GGUF: Full fine-tune
- mradermacher/OpenHermes-2.5-Mistral-7B-i1-GGUF: Quantization
- QuantFactory/OpenHermes-Emojitron-001-GGUF: Full fine-tune
- DevQuasar/teknium.OpenHermes-2.5-Mistral-7B-GGUF: Same weights, converted
- nold/OpenHermes-Emojitron-001-GGUF: Full fine-tune
- basiphobe/sci-assistant: Same weights, converted
- ddty555/OpenHermes-2.5-Mistral-7B-GGUF: Quantization
- mlabonne/NeuralHermes-2.5-Mistral-7B-GGUF: Quantization
- cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5: Full fine-tune
- mlabonne/NeuralHermes-2.5-Mistral-7B: LoRA-style
- openaccess-ai-collective/DPOpenHermes-7B-v2: Full fine-tune
- openaccess-ai-collective/DPOpenHermes-7B: Full fine-tune
- argilla/CapybaraHermes-2.5-Mistral-7B: LoRA-style
- beowolx/MistralHermes-CodePro-7B-v1: LoRA-style
- mlabonne/NeuralHermes-2.5-Mistral-7B-laser: Full fine-tune
- joey00072/ToxicHermes-2.5-Mistral-7B: LoRA-style
- rxavier/Taurus-7B-1.0: LoRA-style
- IsakNordgren/OpenHermes-2.5-Mistral-7B-x2: Same weights, repacked
- runkai/PascalHermes-2.5-Mistral-7B: LoRA-style
- movaxbx/OpenHermes-Emojitron-001: LoRA-style
- CorticalStack/mistral-7b-neuralhermes-2.5-dpo: LoRA-style
11 other repos hold byte-for-byte identical weight files.