Instructions to use KaraKaraWarehouse/CavesOfQwen3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KaraKaraWarehouse/CavesOfQwen3 with Transformers:

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

pipe = pipeline("text-generation", model="KaraKaraWarehouse/CavesOfQwen3")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KaraKaraWarehouse/CavesOfQwen3")
model = AutoModelForCausalLM.from_pretrained("KaraKaraWarehouse/CavesOfQwen3")
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 KaraKaraWarehouse/CavesOfQwen3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KaraKaraWarehouse/CavesOfQwen3"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "KaraKaraWarehouse/CavesOfQwen3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KaraKaraWarehouse/CavesOfQwen3

SGLang

How to use KaraKaraWarehouse/CavesOfQwen3 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 "KaraKaraWarehouse/CavesOfQwen3" \
    --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": "KaraKaraWarehouse/CavesOfQwen3",
		"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 "KaraKaraWarehouse/CavesOfQwen3" \
        --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": "KaraKaraWarehouse/CavesOfQwen3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use KaraKaraWarehouse/CavesOfQwen3 with Docker Model Runner:
```
docker model run hf.co/KaraKaraWarehouse/CavesOfQwen3
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

CavesOfQwen3

Hey Hey, Model Gang, KaraWitch Here.
Have you, ever merged too deeply.
And found something 'they' don't want you to know?
"CavesOfQwen3", who is she? And why can't I reach her?

CavesOfQwen3 is a merge between the base model and the instruct model of Qwen3-30B-A3B (i.e. Qwen3-30B-A3B) and it's base model Qwen3-30B-A3B-base.

The idea for this merge is to remove the overbaked feeling that is in the instruct while retaining the instruct within the model.
I've tested the model and it seems to performs reasonably well*

*(Ignoring the fact that it's spewing something random at the end. I suspect that's on my part in the configuration of the model on vllm or SillyTavern.)

This is a merge of pre-trained language models created using ~~mergekit.~~
This model is done with mergekitty. With a couple of code patch to add qwen3 and a o_proj into Qwen3 arch configuration (else vllm get's very grumpy over it.)
This was me when I found out it didn't have o_proj.

Thankfully merging can be done on CPU. But not inference!

I used TIES. Not because I'm lazy but because it's what I had lying around that isn't SCE or something else.

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen3-30B-A3B as a base.

Models Merged

The following models were included in the merge:

Qwen/Qwen3-30B-A3B-Base

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: Qwen/Qwen3-30B-A3B
    parameters:
      density: 0.4
      weight: 0.35
  - model: Qwen/Qwen3-30B-A3B-Base
    parameters:
      density: 0.7
      weight: 1

merge_method: ties
base_model: Qwen/Qwen3-30B-A3B
parameters:
  normalize: true
dtype: bfloat16

Disclaimer.

CavesOfQwen3 and it's creator is not affiliated with Caves Of Qud or the creator of the video linked.
The reference is intentional, but it is supposed to be taken as a light hearted joke. There's not need to take it too deeply other than "Haha, funni name." This disclaimer is for those who think otherwise or are overthinkers.

Downloads last month: 1

Safetensors

Model size

31B params

Tensor type

BF16

Model tree for KaraKaraWarehouse/CavesOfQwen3

Qwen/Qwen3-30B-A3B

Qwen/Qwen3-30B-A3B-Base

Merge model

this model

Quantizations

2 models

Paper for KaraKaraWarehouse/CavesOfQwen3

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19