Instructions to use Inceptive/ROLEPL-AI-v2-Qwen2.5-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Inceptive/ROLEPL-AI-v2-Qwen2.5-7B with Transformers:

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

pipe = pipeline("text-generation", model="Inceptive/ROLEPL-AI-v2-Qwen2.5-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Inceptive/ROLEPL-AI-v2-Qwen2.5-7B")
model = AutoModelForCausalLM.from_pretrained("Inceptive/ROLEPL-AI-v2-Qwen2.5-7B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Inceptive/ROLEPL-AI-v2-Qwen2.5-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Inceptive/ROLEPL-AI-v2-Qwen2.5-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inceptive/ROLEPL-AI-v2-Qwen2.5-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Inceptive/ROLEPL-AI-v2-Qwen2.5-7B

SGLang

How to use Inceptive/ROLEPL-AI-v2-Qwen2.5-7B 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 "Inceptive/ROLEPL-AI-v2-Qwen2.5-7B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inceptive/ROLEPL-AI-v2-Qwen2.5-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Inceptive/ROLEPL-AI-v2-Qwen2.5-7B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Inceptive/ROLEPL-AI-v2-Qwen2.5-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Inceptive/ROLEPL-AI-v2-Qwen2.5-7B with Docker Model Runner:
```
docker model run hf.co/Inceptive/ROLEPL-AI-v2-Qwen2.5-7B
```

Bad license will hurt this good project

by CyborgPaloma - opened Aug 28, 2025

Discussion

CyborgPaloma

Aug 28, 2025

This is a really, REALLY cool project, but I'm pretty sad you thought DailyDialogue was worth a CC by NC SA 4.0 (assuming that is why, can't see any other reason). Unfortunately I think that is going to stop this great work in the water for a lot of cases, but I really wish you folks success and encourage you to prioritize permissive licensing in the future. Hopefully someone will distill the 70b for you or something to break the license, fingers crossed, as this is a lot of work and training and it'd be nice if you could fully reap the rewards.

abelalonso

Inceptive org Aug 29, 2025

Thanks for your interest in the project. Unfortunately the license choice was made by the use of DailyDialogue (which was an important part of the fine-tuning set). As a derivative job of DailyDialogue, we are forced to publish under this version.

CyborgPaloma changed discussion title from Bad liscense will hurt this good project to Bad license will hurt this good project Sep 1, 2025

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment