Instructions to use anthracite-org/magnum-v1-72b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anthracite-org/magnum-v1-72b with Transformers:

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

pipe = pipeline("text-generation", model="anthracite-org/magnum-v1-72b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anthracite-org/magnum-v1-72b")
model = AutoModelForCausalLM.from_pretrained("anthracite-org/magnum-v1-72b", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use anthracite-org/magnum-v1-72b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "anthracite-org/magnum-v1-72b"
# 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-v1-72b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/anthracite-org/magnum-v1-72b

SGLang

How to use anthracite-org/magnum-v1-72b 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-v1-72b" \
    --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-v1-72b",
		"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-v1-72b" \
        --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-v1-72b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use anthracite-org/magnum-v1-72b with Docker Model Runner:
```
docker model run hf.co/anthracite-org/magnum-v1-72b
```

Learning rate scheduler

by deleted - opened Jul 4, 2024

Discussion

deleted

Jul 4, 2024

Hi,

I'm currently looking into adding a new learning rate scheduler to Transformers, which I call "staggered linear LR" https://github.com/huggingface/transformers/pull/31742 . The way it works is, it keeps a constant learning rate throughout the entire epoch, and then modifies it linearly at each new epoch, thus giving every part of the dataset an equal learning rate in the training process, while still allowing for LR dropping during training. The only caveat being that you need to train for more than 1 epoch.

Two questions:

What learning rate/scheduler do you usually use? Does it differ depending on the model or dataset? (E.g. different LR for big vs small models, etc)
Do you ever train more than 1 epoch?

Thanks.

alpindale

Jul 6, 2024

(I'm unsure why you're asking about this here but...) we discussed different approaches to learning rate too, something along the lines of what you have here. Essentially, warmup at the start, constant for most of the run, and a cooldown towards the end. We didn't go with it because none of the training frameworks had anything like this.

deleted

Jul 7, 2024

Hi! Thanks for the response. I'm sorry, I didn't know where else to reach you. Is there a Discord or something where you guys hang out? :) Would love to join if so.

As for your response, it sounds like what I am proposing would be potentially useful at least for experimentation.

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