Instructions to use DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT with Transformers:

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

pipe = pipeline("text-generation", model="DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT")
model = AutoModelForCausalLM.from_pretrained("DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT")
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 DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT

SGLang

How to use DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT 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 "DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT" \
    --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": "DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT",
		"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 "DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT" \
        --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": "DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT with Docker Model Runner:
```
docker model run hf.co/DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Model Card for Llama-3.3-Argunaut-1-70B-SFT

This model is a fine-tuned version of meta-llama/Llama-3.3-70B-Instruct. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "Are you familiar with Argdown syntax? What's its purpose?"
generator = pipeline("text-generation", model="DebateLabKIT/Llama-3.1-Argunaut-1-8B-SFT", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

SFT dataset mixture

Dataset	Weight (examples)	Weight (tokens)
DebateLabKIT/deepa2-conversations	25%	49%
DebateLabKIT/deep-argmap-conversations	25%	18%
allenai/tulu-3-sft-mixture	50%	33%

Training procedure

Trained with SFT on 1M examples and for 1 epoch with

context length 8196
packing (trl implementation)
spectrum (top 30 percent)

# Training parameters
num_train_epochs: 1
per_device_train_batch_size: 2
gradient_accumulation_steps: 8
gradient_checkpointing: true
gradient_checkpointing_kwargs:
  use_reentrant: false
learning_rate: 2.0e-6  # following _Tülu 3_ recipe
lr_scheduler_type: cosine
warmup_ratio: 0.1

Hardware: 4 x H100 GPUs.

This work was performed on the HoreKa supercomputer funded by the Ministry of Science, Research and the Arts Baden-Württemberg and by the Federal Ministry of Education and Research.

Framework versions

TRL: 0.12.1
Transformers: 4.46.3
Pytorch: 2.4.1
Datasets: 3.1.0
Tokenizers: 0.20.3

Credits

This work wouldn't be possible without all the great contributions from the open LLM community. Thank you! Special kudos go to

@philschmid for his latest fine-tuning boilerplate
@lvwerra, @lewtun et al for building and maintaining trl
@cognitivecomputations for sharing spectrum
@allenai for the Tülu recipe and artifacts

Downloads last month: 6

Safetensors

Model size

71B params

Tensor type

BF16

Model tree for DebateLabKIT/Llama-3.3-Argunaut-1-70B-SFT

Base model

meta-llama/Llama-3.1-70B

Finetuned

meta-llama/Llama-3.3-70B-Instruct

Finetuned

(614)

this model

Finetunes

1 model

Quantizations

3 models

DebateLabKIT
/

Llama-3.3-Argunaut-1-70B-SFT