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, AutoModelForMultimodalLM

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

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
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is the second in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of Qwen1.5 32B.

Prompting

Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:

"""<|im_start|>user
Hi there!<|im_end|>
<|im_start|>assistant
Nice to meet you!<|im_end|>
<|im_start|>user
Can I ask a question?<|im_end|>
<|im_start|>assistant
"""

Credits

Three new general purpose instruction following datasets were added on top of the original Stheno dataset (which had certain low quality entries purged/removed). The first two were designed specifically for the Magnum series, to better address prompt adherence and coherence:

kalomaze/Opus_Instruct_25k
Nopm/Opus_WritingStruct
Gryphe/Sonnet3.5-SlimOrcaDedupCleaned (A ~16k rows subset)

This model has been a team effort, and the credits goes to all members of Anthracite.

Training

The training was done for 2 epochs with a learning rate of 1e-05. We used 8x NVIDIA H100 Tensor Core GPUs for the full-parameter fine-tuning of the model.