Instructions to use Yhyu13/LMCocktail-Mistral-7B-v1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Yhyu13/LMCocktail-Mistral-7B-v1 with Transformers:

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

pipe = pipeline("text-generation", model="Yhyu13/LMCocktail-Mistral-7B-v1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Yhyu13/LMCocktail-Mistral-7B-v1")
model = AutoModelForCausalLM.from_pretrained("Yhyu13/LMCocktail-Mistral-7B-v1", 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 Yhyu13/LMCocktail-Mistral-7B-v1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Yhyu13/LMCocktail-Mistral-7B-v1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Yhyu13/LMCocktail-Mistral-7B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Yhyu13/LMCocktail-Mistral-7B-v1

SGLang

How to use Yhyu13/LMCocktail-Mistral-7B-v1 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 "Yhyu13/LMCocktail-Mistral-7B-v1" \
    --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": "Yhyu13/LMCocktail-Mistral-7B-v1",
		"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 "Yhyu13/LMCocktail-Mistral-7B-v1" \
        --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": "Yhyu13/LMCocktail-Mistral-7B-v1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Yhyu13/LMCocktail-Mistral-7B-v1 with Docker Model Runner:
```
docker model run hf.co/Yhyu13/LMCocktail-Mistral-7B-v1
```

LMCocktail-Mistral-7B-v1 / scripts /merge.py

yhyu13

Upload

1108a1c over 2 years ago

Raw

History Blame Contribute Delete

1.18 kB

	from LM_Cocktail import mix_models_by_layers
	import argparse

	if __name__ == "__main__":

	parser = argparse.ArgumentParser()
	parser.add_argument("--model_type", type=str, default="decoder", help="Type of model to be mixed")
	parser.add_argument("--output_path", type=str, default="./mixed_llm", help="Path to save the mixed model")
	parser.add_argument("--max_length", type=int, default=100, help="Maximum length of the sequence to be generated")
	parser.add_argument("--models", type=str, nargs='+', default=["meta-llama/Llama-2-7b-chat-hf", "Shitao/llama2-ag-news"], help="Path to the models to be mixed")
	parser.add_argument("--weights", type=float, nargs='+', default=[0.7, 0.3], help="Weights of the models to be mixed")
	parser.add_argument("--save_precision", type=str, default='float32', help="mixed model saved format")
	args = parser.parse_args()

	# Mix Large Language Models (LLMs) and save the combined model to the path: ./mixed_llm
	model = mix_models_by_layers(
	model_names_or_paths=args.models,
	model_type=args.model_type,
	weights=args.weights,
	output_path=args.output_path)

	print(model)