Hugging Face's logo

nbeerbower
/
Dumpling-Qwen2.5-VL-7B

Image-Text-to-Text
Safetensors
English
qwen2_5_vl
multimodal
uncensored
conversational
Model card Files Community
3
Dumpling-Qwen2.5-VL-7B / README.md
nbeerbower's picture
nbeerbower
Update README.md
392a81a verified
preview code
|
raw
history blame contribute delete
2.23 kB
metadata
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct/blob/main/LICENSE
language:
  - en
pipeline_tag: image-text-to-text
tags:
  - multimodal
  - uncensored
datasets:
  - nbeerbower/GreatFirewall-DPO
  - nbeerbower/Schule-DPO
  - nbeerbower/Purpura-DPO
  - nbeerbower/Arkhaios-DPO
  - jondurbin/truthy-dpo-v0.1
  - antiven0m/physical-reasoning-dpo
  - flammenai/Date-DPO-NoAsterisks
  - flammenai/Prude-Phi3-DPO
  - Atsunori/HelpSteer2-DPO
  - jondurbin/gutenberg-dpo-v0.1
  - nbeerbower/gutenberg2-dpo
  - nbeerbower/gutenberg-moderne-dpo
base_model:
  - huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated

image/png

Dumpling-Qwen2.5-VL-7B

Shout-out to @huihui-ai for the abliterated model!

huihui-ai/Qwen2.5-VL-7B-Instruct-abliterated finetuned on:

Method

QLoRA ORPO tuned with 1x RTX A6000 for 2 epochs.