Instructions to use FlareRebellion/WeirdCompound-v1.7-24b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FlareRebellion/WeirdCompound-v1.7-24b with Transformers:

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

pipe = pipeline("text-generation", model="FlareRebellion/WeirdCompound-v1.7-24b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FlareRebellion/WeirdCompound-v1.7-24b")
model = AutoModelForCausalLM.from_pretrained("FlareRebellion/WeirdCompound-v1.7-24b", device_map="auto")
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 FlareRebellion/WeirdCompound-v1.7-24b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FlareRebellion/WeirdCompound-v1.7-24b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FlareRebellion/WeirdCompound-v1.7-24b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FlareRebellion/WeirdCompound-v1.7-24b

SGLang

How to use FlareRebellion/WeirdCompound-v1.7-24b 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 "FlareRebellion/WeirdCompound-v1.7-24b" \
    --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": "FlareRebellion/WeirdCompound-v1.7-24b",
		"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 "FlareRebellion/WeirdCompound-v1.7-24b" \
        --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": "FlareRebellion/WeirdCompound-v1.7-24b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FlareRebellion/WeirdCompound-v1.7-24b with Docker Model Runner:
```
docker model run hf.co/FlareRebellion/WeirdCompound-v1.7-24b
```

Works with image input!

by GeoMaciolek - opened Feb 25

Discussion

GeoMaciolek

Feb 25

At least decently well - this is probably old news for lots of people, but on a whim I tried the mmproj from mistralai/Mistral-Small-3.2-24B-Instruct-2506 (Specifically this bf16 from bartowski's GGUF) and applied it in llama.cpp, and it worked pretty decently! Just figured I'd mention it to anyone who might be curious to try it. (Especially given that at least at some point in its life, WeirdCompound had a textonly model in there, it seems?)

sidran

May 17

Interesting! I just came to praise this model after testing properly abliterated Qwen3.6 and Gemma 4. Thanks

sidran

May 18

Confirmed, works for me as well.

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