Instructions to use ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated

SGLang

How to use ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated with Docker Model Runner:
```
docker model run hf.co/ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated
```

Qwen2.5-VL-7B-Instruct-abliterated (Merged FP16)

This repository contains the merged FP16 weights of the abliterated version of Qwen2.5-VL-7B-Instruct.

I have simply merged the split files originally provided by ussoewwin into a unified model for easier handling and deployment.

Model Details

Model Type: Vision-Language Model (Qwen2.5-VL)
Base Model: Qwen/Qwen2.5-VL-7B-Instruct
Modification: Abliterated (Safety mechanisms/refusals modified)
Source of Split Files: ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated
Precision: FP16

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for ussoewwin/Qwen2.5-VL-7B-Instruct-abliterated

Base model

Qwen/Qwen2.5-VL-7B-Instruct

Finetuned

(1073)

this model