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

Libraries

How to use mlabonne/AlphaMonarch-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlabonne/AlphaMonarch-7B")
model = AutoModelForCausalLM.from_pretrained("mlabonne/AlphaMonarch-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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use mlabonne/AlphaMonarch-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlabonne/AlphaMonarch-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": "mlabonne/AlphaMonarch-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlabonne/AlphaMonarch-7B

SGLang

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

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

Low quality responses compared to NeuralBeagle14 on KCPP using q8

by deleted - opened Feb 28, 2024

Discussion

deleted

Feb 28, 2024

I don't know how to make this model work as it should, for me it's far from being as good as neuralbeagle14 for conversation AND roleplay, did anybody else notice that and managed to find a fix please? I'd like to use the intended potential of the model...

mlabonne

Owner Feb 29, 2024

Not the fix you're looking for, but can you try Monarch-7B? I made GGUFs for you: https://huggingface.co/mlabonne/Monarch-7B-GGUF/tree/main

In my tests, NeuralBeagle14 was terrible at conversation and RP but maybe it depends on the use case.

NoThankYou1

Mar 1, 2024

Not the fix you're looking for, but can you try Monarch-7B? I made GGUFs for you: https://huggingface.co/mlabonne/Monarch-7B-GGUF/tree/main

In my tests, NeuralBeagle14 was terrible at conversation and RP but maybe it depends on the use case.

What's the prompt format for AlphaMonarch 7b?

mlabonne

Owner Mar 1, 2024

What's the prompt format for AlphaMonarch 7b?

Mistral Instruct.

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