Instructions to use ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3 with Transformers:

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

pipe = pipeline("text-generation", model="ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3

SGLang

How to use ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3 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 "ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3" \
    --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": "ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3",
		"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 "ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3" \
        --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": "ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3 with Docker Model Runner:
```
docker model run hf.co/ArtusDev/soob3123_GrayLine-Qwen3-8B-EXL3
```

ArtusDev commited on Jun 29, 2025

Commit

e05f406

verified ·

1 Parent(s): b284aac

Update README.md

Browse files

Files changed (1) hide show

README.md +17 -0

README.md CHANGED Viewed

@@ -2,6 +2,23 @@
 base_model: soob3123/GrayLine-Qwen3-8B
 base_model_relation: quantized
 quantized_by: ArtusDev
 ---
 ## EXL3 Quants of soob3123/GrayLine-Qwen3-8B

 base_model: soob3123/GrayLine-Qwen3-8B
 base_model_relation: quantized
 quantized_by: ArtusDev
+pipeline_tag: text-generation
+library_name: transformers
+language:
+- en
+tags:
+- text-generation
+- uncensored
+- direct-answer
+- information-retrieval
+- general-knowledge
+- unfiltered
+- amoral-ai
+- exl3
+datasets:
+- soob3123/GrayLine-QA
+- soob3123/GrayLine-QA-Reasoning
+license: apache-2.0
 ---
 ## EXL3 Quants of soob3123/GrayLine-Qwen3-8B