Instructions to use ChaoticNeutrals/Community_Request-03-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ChaoticNeutrals/Community_Request-03-12B with Transformers:

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

pipe = pipeline("text-generation", model="ChaoticNeutrals/Community_Request-03-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ChaoticNeutrals/Community_Request-03-12B")
model = AutoModelForCausalLM.from_pretrained("ChaoticNeutrals/Community_Request-03-12B")
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]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use ChaoticNeutrals/Community_Request-03-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ChaoticNeutrals/Community_Request-03-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ChaoticNeutrals/Community_Request-03-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ChaoticNeutrals/Community_Request-03-12B

SGLang

How to use ChaoticNeutrals/Community_Request-03-12B 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 "ChaoticNeutrals/Community_Request-03-12B" \
    --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": "ChaoticNeutrals/Community_Request-03-12B",
		"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 "ChaoticNeutrals/Community_Request-03-12B" \
        --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": "ChaoticNeutrals/Community_Request-03-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ChaoticNeutrals/Community_Request-03-12B with Docker Model Runner:
```
docker model run hf.co/ChaoticNeutrals/Community_Request-03-12B
```

He's cooking...!

by Lewdiculous - opened Mar 22, 2025

Discussion

Lewdiculous

Mar 22, 2025

These from Discord?

Nitral-AI

The Chaotic Neutrals org Mar 22, 2025

•

edited Mar 22, 2025

Someone in the discord discussion thread asked if I had planned to create a Wayfarer version of the GRPO models. Since my training setup is still down, I suggested they merge it into the existing models themselves. To facilitate this, I devised three different merging approaches. However, they ultimately didn't feel comfortable performing the merges, so I ended up handling them myself. Unsure of what to name them, I decided on Community_Request(0x) as a placeholder. I haven't had the opportunity to test their performance yet, as I've been focused on 4bpw EXL2 quantization.

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