Instructions to use Delta-Vector/Rei-24B-KTO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Delta-Vector/Rei-24B-KTO with Transformers:

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

pipe = pipeline("text-generation", model="Delta-Vector/Rei-24B-KTO")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Delta-Vector/Rei-24B-KTO")
model = AutoModelForMultimodalLM.from_pretrained("Delta-Vector/Rei-24B-KTO")
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 Settings

vLLM

How to use Delta-Vector/Rei-24B-KTO with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Delta-Vector/Rei-24B-KTO"
# 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-24B-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Delta-Vector/Rei-24B-KTO

SGLang

How to use Delta-Vector/Rei-24B-KTO 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-24B-KTO" \
    --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-24B-KTO",
		"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-24B-KTO" \
        --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-24B-KTO",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Delta-Vector/Rei-24B-KTO with Docker Model Runner:
```
docker model run hf.co/Delta-Vector/Rei-24B-KTO
```

Extremely Underrated

by cactopus - opened Sep 19, 2025

Discussion

cactopus

Sep 19, 2025

•

edited Sep 23, 2025

There are exl3 quants currently available https://huggingface.co/DeathGodlike/Rei-24B-KTO_EXL3 and I suggest people to test it out.
Severely underrated, passes my homebrewed logic tests consistently, and the outputs are varied and make each generation interesting.

Currently my go-to model for RP, and I have tested many. Better logic capabilities (and more verbose, but conciseness is a subjective preference) than the new Austral 32B GLM4 Winton (tested q6), better output and logic than Archaeo 32B (q6) and latest (<70B) ReadyArt models. Highly recommended. Can fit exl3 8bpw with a 89600 context within a dual 24G GPU setup (and much more in lower quants, which can fit inside a single GPU comfortably).

Seems to be compatible with Alpaca formatting as well, and it gets rid of some formatting issues with Mistral V7 Tekken while using impersonate in ST.

cactopus changed discussion title from Extremely Underrated. to Extremely Underrated Sep 19, 2025

Delta-Vector

Owner Oct 2, 2025

Glad you liked it! =)

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