Instructions to use macadeliccc/MonarchLake-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use macadeliccc/MonarchLake-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("macadeliccc/MonarchLake-7B")
model = AutoModelForCausalLM.from_pretrained("macadeliccc/MonarchLake-7B")
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 macadeliccc/MonarchLake-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/macadeliccc/MonarchLake-7B

SGLang

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

Docker Model Runner
How to use macadeliccc/MonarchLake-7B with Docker Model Runner:
```
docker model run hf.co/macadeliccc/MonarchLake-7B
```

Random characters showing up

by aaha - opened Mar 6, 2024

Discussion

aaha

Mar 6, 2024

Hi @macadeliccc
So i have been trying this model and it follows instruction quiet well. But it also randomly adds characters such as /istribute: assistant:. Other than stop sequence, is there a way to prevent this or such non-english proper words from showing up?

Also, there was some issue observed with westlake models with multilingual text randomly showing up, where the model switches language on its own. Have you noticed that? Is that something fixed in this?

Thanks again!

macadeliccc

Owner Mar 6, 2024

I have not noticed this before. However, it can be a common byproduct of a merge. I will do some further testing on this model and see if I can find a specific reason.

In the meantime, try WestLake-7b-v2-laser-truthy-dpo or OmniCorso-7B.

They are similar models that have been tested more.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment