Instructions to use anthracite-org/magnum-v1-32b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anthracite-org/magnum-v1-32b with Transformers:

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

pipe = pipeline("text-generation", model="anthracite-org/magnum-v1-32b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anthracite-org/magnum-v1-32b")
model = AutoModelForCausalLM.from_pretrained("anthracite-org/magnum-v1-32b")
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

vLLM

How to use anthracite-org/magnum-v1-32b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anthracite-org/magnum-v1-32b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "anthracite-org/magnum-v1-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anthracite-org/magnum-v1-32b

SGLang

How to use anthracite-org/magnum-v1-32b 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 "anthracite-org/magnum-v1-32b" \
    --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": "anthracite-org/magnum-v1-32b",
		"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 "anthracite-org/magnum-v1-32b" \
        --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": "anthracite-org/magnum-v1-32b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anthracite-org/magnum-v1-32b with Docker Model Runner:
```
docker model run hf.co/anthracite-org/magnum-v1-32b
```

great model - any chance of qwen update?

by nacs - opened Sep 21, 2024

Discussion

nacs

Sep 21, 2024

•

edited Sep 21, 2024

magnum is one of my favorite models.

any chance we can get a magnum based off the new qwen 2.5 32B? (this one is qwen 1.5 looks like).

thanks.

Delta-Vector

Anthracite org Sep 21, 2024

Possibly. We've still yet to experiment with the new 32b - In the meanwhile it's worth trying out our 27B and 34B (Based off Gemma and Yi respectively)

DazzlingXeno

Sep 21, 2024

Yes please 🙂

nacs

Sep 21, 2024

•

edited Sep 21, 2024

I’ve been using the 34b and it is indeed good but the new qwen 2.5 32b is benchmarking higher than some 70Bs at the moment

jeiku

Sep 21, 2024

I’ve been using the 34b and it is indeed good but the new qwen 2.5 32b is benchmarking higher than some 70Bs at the moment

I would take the qwen benches with a grain of salt if I were you. Admittedly, I haven't tried fine-tuning anything bigger than the 7B, but performance was below a minitron 8B tuned on the exact same data. Not to mention the apparent filtering of pretrain data.

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