FOXAI SEARCH
サイト内検索
AI モデル 85005
- NeuralDaredevil-8B-abliterated-GGUF↗
QuantFactory
This is a DPO fine-tune of mlabonne/Daredevil-8-abliterated, trained on one epoch of mlabonne/orpo-dpo-mix-40k. The DPO fine-tuning successfully recovers the performance loss due to the abliteration process, making it an excellent uncensored model. You can use it for any application that doesn't require alignment, like role-playing. Tested on LM Studio using the "Llama 3" preset. NeuralDaredevil-8B is the best-performing uncensored 8B model on the Open LLM Leaderboard (MMLU score).
- W25_Realistic_I2V↗
r4tn4
- BeaverAI_Spectre-37B-v1a↗
ReadyArt
- ajibawa-2023_-_WikiHow-Mistral-Instruct-7B-gguf↗
RichardErkhov
- BroAlanTaps_-_GPT2-large-128-12000steps-gguf↗
RichardErkhov
- mistralai_-_Mistral-7B-Instruct-v0.3-gguf↗
RichardErkhov
- yuntian-deng_-_gpt2-explicit-cot-multiplication-20-digits-gguf↗
RichardErkhov
- Llama-3.1-CyberAlpha8B↗
Rumiii
- Sailor2-1B↗
sail
- sot-phase2-wikitext103-heuristic-seed42-tc768d013-v8-tailfreeze↗
sbartlett97
