Instructions to use KaraKaraWarehouse/StackedBlenderCartel-llama33-120B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use KaraKaraWarehouse/StackedBlenderCartel-llama33-120B with Transformers:

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

pipe = pipeline("text-generation", model="KaraKaraWarehouse/StackedBlenderCartel-llama33-120B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("KaraKaraWarehouse/StackedBlenderCartel-llama33-120B")
model = AutoModelForCausalLM.from_pretrained("KaraKaraWarehouse/StackedBlenderCartel-llama33-120B")
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/StackedBlenderCartel-llama33-120B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "KaraKaraWarehouse/StackedBlenderCartel-llama33-120B"
# 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/StackedBlenderCartel-llama33-120B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/KaraKaraWarehouse/StackedBlenderCartel-llama33-120B

SGLang

How to use KaraKaraWarehouse/StackedBlenderCartel-llama33-120B 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/StackedBlenderCartel-llama33-120B" \
    --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/StackedBlenderCartel-llama33-120B",
		"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/StackedBlenderCartel-llama33-120B" \
        --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/StackedBlenderCartel-llama33-120B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use KaraKaraWarehouse/StackedBlenderCartel-llama33-120B with Docker Model Runner:
```
docker model run hf.co/KaraKaraWarehouse/StackedBlenderCartel-llama33-120B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

KaraKaraWitch/StackedBlenderCartel-llama33-120B

This is a merge of pre-trained language models created using mergekitty.

But... WHY?!

... A stupid idea crept into my mind when I saw that I have 2 70B models of pretty good (:TM:) quality.

You could make a stacked model out of this.

So... here we are.

I know, contrary to what people have told us countless times not to do it, here we are once again with a stupid idea.

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:


slices:
  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt1
      layer_range: [0, 16]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt2
      layer_range: [8, 24]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt1
      layer_range: [17, 32]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt2
      layer_range: [25, 40]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt1
      layer_range: [33, 48]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt2
      layer_range: [41, 56]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt1
      layer_range: [49, 64]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt2
      layer_range: [57, 72]

  - sources:
    - model: KaraKaraWitch/BlenderCartel-llama33-70B-Pt1
      layer_range: [65, 80]

merge_method: passthrough
dtype: float16

Downloads last month: 1

Safetensors

Model size

119B params

Tensor type

F16

Model tree for KaraKaraWarehouse/StackedBlenderCartel-llama33-120B

KaraKaraWitch/BlenderCartel-llama33-70B-Pt1

KaraKaraWitch/BlenderCartel-llama33-70B-Pt2

Merge model

this model

Quantizations

2 models