Instructions to use h34v7/DXP-Zero-V1.2-24b-Small-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use h34v7/DXP-Zero-V1.2-24b-Small-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="h34v7/DXP-Zero-V1.2-24b-Small-Instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("h34v7/DXP-Zero-V1.2-24b-Small-Instruct")
model = AutoModelForCausalLM.from_pretrained("h34v7/DXP-Zero-V1.2-24b-Small-Instruct")
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
Local Apps Settings

vLLM

How to use h34v7/DXP-Zero-V1.2-24b-Small-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "h34v7/DXP-Zero-V1.2-24b-Small-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "h34v7/DXP-Zero-V1.2-24b-Small-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/h34v7/DXP-Zero-V1.2-24b-Small-Instruct

SGLang

How to use h34v7/DXP-Zero-V1.2-24b-Small-Instruct 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 "h34v7/DXP-Zero-V1.2-24b-Small-Instruct" \
    --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": "h34v7/DXP-Zero-V1.2-24b-Small-Instruct",
		"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 "h34v7/DXP-Zero-V1.2-24b-Small-Instruct" \
        --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": "h34v7/DXP-Zero-V1.2-24b-Small-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use h34v7/DXP-Zero-V1.2-24b-Small-Instruct with Docker Model Runner:
```
docker model run hf.co/h34v7/DXP-Zero-V1.2-24b-Small-Instruct
```

Why V1.2.0 instead of V1.3.0?

by ThijsL202 - opened Jun 2, 2025

Discussion

ThijsL202

Jun 2, 2025

May I ask why you merged with Dans-PersonalityEngine-V1.2.0-24b instead of Dans-PersonalityEngine-V1.3.0-24b? Personal preference? Something else? Also, do you think it's worth using this merge instead for coherence? Thanks.

h34v7

Owner Jun 2, 2025

At the time of this merge there is only PersonalityEngine-V1.2.0-24b it took a while to upload with my internet and by the time it uploaded Dans-PersonalityEngine-V1.3.0-24b dropped. Well a bit unfortunate maybe next version I will use the latest V1.3.0 instead.

For DXP series it is very coherence and more humanized somehow. Although it lack the initiatives to keep you in your toes unless you told the model otherwise.

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