Instructions to use Delta-Vector/Rei-V2-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Delta-Vector/Rei-V2-12B with Transformers:

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

pipe = pipeline("text-generation", model="Delta-Vector/Rei-V2-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Delta-Vector/Rei-V2-12B")
model = AutoModelForCausalLM.from_pretrained("Delta-Vector/Rei-V2-12B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Delta-Vector/Rei-V2-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Delta-Vector/Rei-V2-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Delta-Vector/Rei-V2-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Delta-Vector/Rei-V2-12B

SGLang

How to use Delta-Vector/Rei-V2-12B 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 "Delta-Vector/Rei-V2-12B" \
    --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": "Delta-Vector/Rei-V2-12B",
		"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 "Delta-Vector/Rei-V2-12B" \
        --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": "Delta-Vector/Rei-V2-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Delta-Vector/Rei-V2-12B with Docker Model Runner:
```
docker model run hf.co/Delta-Vector/Rei-V2-12B
```

wow

by Danioken - opened Apr 5, 2025

Discussion

Danioken

Apr 5, 2025

Your model is doing great for only 12B, would you consider doing something similar with the mistral small 3.1 24B? Nemo lacks a bit of intelligence to pin some details, the Mistral small would be better at that... Plus I'd really like to see what you could do with this model.

Delta-Vector

Owner Apr 6, 2025

Don't have the funds nor the Compute for the model as of now.
https://ko-fi.com/deltavector
If you want, you can donate to my ko-fi and i'll be able to do one in the future. I need something that i can stick into 1 16gb gpu anyway

Danioken changed discussion status to closed Apr 6, 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