Instructions to use alansmithee-cpu/experimental_merge_091026 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use alansmithee-cpu/experimental_merge_091026 with Transformers:

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

pipe = pipeline("text-generation", model="alansmithee-cpu/experimental_merge_091026")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("alansmithee-cpu/experimental_merge_091026")
model = AutoModelForCausalLM.from_pretrained("alansmithee-cpu/experimental_merge_091026", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use alansmithee-cpu/experimental_merge_091026 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alansmithee-cpu/experimental_merge_091026"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "alansmithee-cpu/experimental_merge_091026",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/alansmithee-cpu/experimental_merge_091026

SGLang

How to use alansmithee-cpu/experimental_merge_091026 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 "alansmithee-cpu/experimental_merge_091026" \
    --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": "alansmithee-cpu/experimental_merge_091026",
		"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 "alansmithee-cpu/experimental_merge_091026" \
        --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": "alansmithee-cpu/experimental_merge_091026",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use alansmithee-cpu/experimental_merge_091026 with Docker Model Runner:
```
docker model run hf.co/alansmithee-cpu/experimental_merge_091026
```

(Details to be added)

This model is an experimental merge of the following:

SteelStorage/ML-MS-Etheris-123B
MarsupialAI/Monstral-123B-v2
TheDrummer/Behemoth-ReduX-123B-v1.1
TheDrummer/Behemoth-X-123B-v2.2
Doctor-Shotgun/ML2-123B-Magnum-Diamond
anthracite-org/magnum-v4-123b
Aratako/Amaterasu-123B
gghfez/Writer-Large-2411-v2.1
nbeerbower/Gigaberg-Mistral-Large-123B
migtissera/Tess-R1-Ballad-Mistral-Large-2-123B (taken down by the author, pulled from personal archive)

Disclaimer

Still undergoing testing. Due to the lack of necessary computational resources, the performance of this model has yet been tested. In the case where this model outputs gibberish or performs worse than the components, it will be taken down. All feedbacks and/or reports from community are warmly welcomed.

License

All components derive from Mistral Large 123B and are released under the Mistral AI Research License. This merge inherits that license: research and non-commercial use only. Please refer to the individual component model cards for any additional terms.