NousResearch/Nous-Hermes-2-Mistral-7B-DPO
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
10 derivatives checked
- Aryanne/Open-StarLake-Swap-7B: Full fine-tune
- mradermacher/Nous-Hermes-2-Mistral-7B-DPO-i1-GGUF: Quantization
- QuantFactory/Nous-Hermes-2-Mistral-7B-DPO-GGUF: Quantization
- DevQuasar-12/NousResearch.Nous-Hermes-2-Mistral-7B-DPO-GGUF: Same weights, converted
- mradermacher/Nous-Hermes-2-Mistral-7B-DPO-GGUF: Same weights, converted
- qwp4w3hyb/Nous-Hermes-2-Mistral-7B-DPO-iMat-GGUF: Quantization
- aloobun/Cypher-7B: Full fine-tune
- mvpmaster/MistralDpoPearl-7b-slerp: Full fine-tune
- 00000-X/Dolphin-2.6-FC_Hermes-2-DPO: Full fine-tune
- 00000-X/Hermes-2-DPO_WestLake-7B-v2: Full fine-tune
2 other repos hold byte-for-byte identical weight files.