Instructions to use LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2")
model = AutoModelForMultimodalLM.from_pretrained("LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2")
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 LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2

SGLang

How to use LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2 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 "LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2" \
    --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": "LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2",
		"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 "LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2" \
        --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": "LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2 with Docker Model Runner:
```
docker model run hf.co/LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2
```

LM-cocktail 10.7B v1

This is a 50%-50% model of the SOLAR model and meow.

https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0

https://huggingface.co/rishiraj/meow

who rank #1 and #2 among models <13B in the https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard by 2023/12/20.

Code

The LM-cocktail is novel technique for merging multiple models https://arxiv.org/abs/2311.13534

Code is backed up by this repo https://github.com/FlagOpen/FlagEmbedding.git

Merging scripts available under the ./scripts folder

Result

The SOLAR model is the first model <30B that can answer this question from my test:

What will AI be like in the year 1010 A.D?

without hullicinating into 1010 A.D is a future time (like other llama2 models)

Models greater than that, like Yi-34B could answer this paradoxic question correctly as well, since it is huge enough.

SOLAR 10.7B output

LMCocktail 10.7B output1

LMCocktail 10.7B output2

Downloads last month: 1

Paper for LoneStriker/LMCocktail-10.7B-v1-5.0bpw-h6-exl2

LM-Cocktail: Resilient Tuning of Language Models via Model Merging

Paper • 2311.13534 • Published Nov 22, 2023 • 3