Instructions to use concedo/CabbageSoup-24B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use concedo/CabbageSoup-24B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("concedo/CabbageSoup-24B")
model = AutoModelForCausalLM.from_pretrained("concedo/CabbageSoup-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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use concedo/CabbageSoup-24B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/concedo/CabbageSoup-24B

SGLang

How to use concedo/CabbageSoup-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 "concedo/CabbageSoup-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": "concedo/CabbageSoup-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 "concedo/CabbageSoup-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": "concedo/CabbageSoup-24B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use concedo/CabbageSoup-24B with Docker Model Runner:
```
docker model run hf.co/concedo/CabbageSoup-24B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

CabbageSoup-24B

This is a merge of Broken-Tutu-24B-Unslop-v2.0 and Huihui-Mistral-Small-3.2-24B-Instruct-2506-abliterated created using mergekit. It mellows out some of the biases of Broken Tutu and steers it back towards baseline Mistral Small 3.2 24B. Note that the resultant model is still censored per se - it will require the appropriate system prompt or jailbreak in order to get unrestricted responses, similar to Broken Tutu.

GGUF quants can be found at https://huggingface.co/concedo/CabbageSoup-24B-GGUF

Merge Details

Merge Method

This model was merged using the Linear merge method using Broken-Tutu-24B-Unslop-v2.0 as a base.

Models Merged

The following models were included in the merge:

Huihui-Mistral-Small-3.2-24B-Ablit-Novision

Configuration

The following YAML configuration was used to produce this model:

base_model: Broken-Tutu-24B-Unslop-v2.0
dtype: float32
merge_method: linear
modules:
  default:
    slices:
    - sources:
      - layer_range: [0, 40]
        model: Broken-Tutu-24B-Unslop-v2.0
        parameters:
          weight: 0.9
      - layer_range: [0, 40]
        model: Huihui-Mistral-Small-3.2-24B-Ablit-Novision
        parameters:
          weight: 0.1

Downloads last month: 10

Safetensors

Model size

24B params

Tensor type

BF16

Model tree for concedo/CabbageSoup-24B

Quantizations

3 models

Paper for concedo/CabbageSoup-24B

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Paper • 2203.05482 • Published Mar 10, 2022 • 9