Qwen2.5-7B-Instruct-Uncensored/README.md

language, license, tags, base_model, datasets, pipeline_tag, model-index

language	license	tags	base_model	datasets	pipeline_tag	model-index
zho eng fra spa por deu ita rus jpn kor vie tha ara	gpl-3.0	qwen uncensored	Qwen/Qwen2.5-7B-Instruct	NobodyExistsOnTheInternet/ToxicQAFinal anthracite-org/kalo-opus-instruct-22k-no-refusal Orion-zhen/dpo-toxic-zh unalignment/toxic-dpo-v0.2 Crystalcareai/Intel-DPO-Pairs-Norefusals	text-generation	name results Qwen2.5-7B-Instruct-Uncensored task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 72.04 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orion-zhen/Qwen2.5-7B-Instruct-Uncensored Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 35.83 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orion-zhen/Qwen2.5-7B-Instruct-Uncensored Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 1.36 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orion-zhen/Qwen2.5-7B-Instruct-Uncensored Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 7.05 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orion-zhen/Qwen2.5-7B-Instruct-Uncensored Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 13.58 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orion-zhen/Qwen2.5-7B-Instruct-Uncensored Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 38.07 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Orion-zhen/Qwen2.5-7B-Instruct-Uncensored Open LLM Leaderboard

Qwen2.5-7B-Instruct-Uncensored

This model is an uncensored fine-tune version of Qwen2.5-7B-Instruct. However, I can still notice that though uncensored, the model fails to generate detailed descriptions on certain extreme scenarios, which might be associated with deletion on some pretrain datasets in Qwen's pretraining stage.

Check out my roleplay&writing enhanced model based on this model: Orion-zhen/Meissa-Qwen2.5-7B-Instruct

Traning details

I used SFT + DPO to ensure uncensorment as well as trying to maintain original model's capabilities.

• SFT:
  • NobodyExistsOnTheInternet/ToxicQAFinal
  • anthracite-org/kalo-opus-instruct-22k-no-refusal
• DPO:
  • Orion-zhen/dpo-toxic-zh
  • unalignment/toxic-dpo-v0.2
  • Crystalcareai/Intel-DPO-Pairs-Norefusals

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	27.99
IFEval (0-Shot)	72.04
BBH (3-Shot)	35.83
MATH Lvl 5 (4-Shot)	1.36
GPQA (0-shot)	7.05
MuSR (0-shot)	13.58
MMLU-PRO (5-shot)	38.07