Instructions to use soob3123/Veiled-Rose-22B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use soob3123/Veiled-Rose-22B with Transformers:

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

pipe = pipeline("text-generation", model="soob3123/Veiled-Rose-22B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("soob3123/Veiled-Rose-22B")
model = AutoModelForCausalLM.from_pretrained("soob3123/Veiled-Rose-22B")
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

vLLM

How to use soob3123/Veiled-Rose-22B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "soob3123/Veiled-Rose-22B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "soob3123/Veiled-Rose-22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/soob3123/Veiled-Rose-22B

SGLang

How to use soob3123/Veiled-Rose-22B 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 "soob3123/Veiled-Rose-22B" \
    --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": "soob3123/Veiled-Rose-22B",
		"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 "soob3123/Veiled-Rose-22B" \
        --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": "soob3123/Veiled-Rose-22B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use soob3123/Veiled-Rose-22B with Docker Model Runner:
```
docker model run hf.co/soob3123/Veiled-Rose-22B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

✧ Veiled Rose ✧

Mystery is at the heart of creativity. That, and surprise...As creative channels, we need to trust the darkness.

Veiled Rose emerges under the moon's knowing glow, an enigmatic presence designed for immersive narrative experiences. This 22B parameter model possesses significant reasoning capabilities and cognitive depth, ideal for weaving intricate roleplay scenarios. Veiled Rose excels at crafting richly atmospheric storytelling where nuanced character interactions and complex mysteries unfold with coherence and perception. Expect narratives shrouded in secrets, driven by sophisticated motivations, and unveiled through compelling, intelligent storytelling.

⋆ Features ⋆

⟡ Deeper Atmospheric Immersion: Even richer, moon-drenched scenarios bloom, now infused with greater intellectual subtlety and environmental awareness.
⟡ Enhanced Reasoning & Consistency: Characters maintain unwavering personas driven by more sophisticated internal logic and demonstrate sharper, more consistent reasoning throughout complex narratives.
⟡ Intricate Narrative Mystery: Enigmatic storylines unfold with greater coherence, logical depth, and the capacity for more complex plot structures and surprising, yet earned, revelations.
⟡ Profound Emotional & Cognitive Nuance: The unspoken, the veiled meanings, and the intricate web of character thoughts and motivations are rendered with heightened clarity and psychological depth.

⋆ Limitations ⋆

Flourishes most in atmospheric, introspective, or character-driven scenarios requiring nuanced interaction.
Due to its depth, may occasionally produce responses that are overly complex or dense for simpler contexts.
Uncensored in Roleplay mode (e.g., SillyTavern), adheres to safety guidelines in Assistant mode (no system prompt).
- Use one of the Amoral models for a fully uncensored but potentially less nuanced experience.

⋆ GGUFs ⋆

Static

Downloads last month: 7

Safetensors

Model size

22B params

Tensor type

BF16

Model tree for soob3123/Veiled-Rose-22B

Quantizations

5 models

Collection including soob3123/Veiled-Rose-22B

Veiled Series

Collection

Models trained to be better at RP • 2 items • Updated Mar 2