Hugging Face's logo

Orion-zhen
/
Qwen2.5-7B-Instruct-Uncensored

Text Generation
Safetensors
Chinese
English
qwen2
qwen
uncensored
conversational
Model card Files Community
Qwen2.5-7B-Instruct-Uncensored / README.md
Orion-zhen's picture
Orion-zhen
Update README.md
33c2465 verified
preview code
|
raw
history blame contribute delete
No virus
1.18 kB
metadata
license: gpl-3.0
datasets:
  - 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
language:
  - zh
  - en
base_model:
  - Qwen/Qwen2.5-7B-Instruct
pipeline_tag: text-generation
tags:
  - qwen
  - uncensored

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