Instructions to use Nexusflow/Athene-V2-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nexusflow/Athene-V2-Chat with Transformers:

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

pipe = pipeline("text-generation", model="Nexusflow/Athene-V2-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nexusflow/Athene-V2-Chat")
model = AutoModelForCausalLM.from_pretrained("Nexusflow/Athene-V2-Chat")
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 Nexusflow/Athene-V2-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nexusflow/Athene-V2-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nexusflow/Athene-V2-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nexusflow/Athene-V2-Chat

SGLang

How to use Nexusflow/Athene-V2-Chat 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 "Nexusflow/Athene-V2-Chat" \
    --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": "Nexusflow/Athene-V2-Chat",
		"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 "Nexusflow/Athene-V2-Chat" \
        --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": "Nexusflow/Athene-V2-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nexusflow/Athene-V2-Chat with Docker Model Runner:
```
docker model run hf.co/Nexusflow/Athene-V2-Chat
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Athene-V2-Chat-72B: Rivaling GPT-4o across Benchmarks

Nexusflow HF - Nexusflow Discord - Athene-V2 Blogpost

We introduce Athene-V2-Chat-72B, an open-weights LLM on-par with GPT-4o across benchmarks. It is currently the best open model according to Chatbot Arena, where it beats GPT-4o-0513 (the best GPT-4o model on Arena) in hard and math category, and is on-par with GPT-4o-0513 in coding, instruction following, longer query and multi-turn.

It is trained through RLHF with Qwen-2.5-72B-Instruct as base model. Athene-V2-Chat-72B excels in chat, math, and coding. Its sister model, Athene-V2-Agent-72B, surpasses GPT-4o in complex function calling and agentic applications.

Developed by: The Nexusflow Team
Model type: Chat Model
Finetuned from model: Qwen 2.5 72B-Instruct
License: Nexusflow Research License
Blog: https://nexusflow.ai/blogs/athene-v2

Usage

Athene-V2-Chat uses the same chat template as Qwen2.5-72B-Instruct. Below is an example simple usage using the Transformers library.

from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "Nexusflow/Athene-V2-Chat"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "Write a Python function to return the nth Fibonacci number in log n runtime."

messages = [
    {"role": "user", "content": prompt}
]

text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)

model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=2048
)

generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

Note that by adding a system prompt that encourages the model to think step by step, the model can improve further on difficult math queries and problems like counting rs in strawberry. For fairness consideration we do not include such system prompt during chat evaluation.

Acknowledgment

We would like to thank the LMSYS Organization for their support of testing the model. We would like to thank Qwen Team and the open source community for their efforts in providing the datasets and base models.