Instructions to use async0x42/Athene-V2-Chat-exl2_3.5bpw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use async0x42/Athene-V2-Chat-exl2_3.5bpw with Transformers:

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

pipe = pipeline("text-generation", model="async0x42/Athene-V2-Chat-exl2_3.5bpw")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("async0x42/Athene-V2-Chat-exl2_3.5bpw")
model = AutoModelForCausalLM.from_pretrained("async0x42/Athene-V2-Chat-exl2_3.5bpw")
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 async0x42/Athene-V2-Chat-exl2_3.5bpw with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "async0x42/Athene-V2-Chat-exl2_3.5bpw"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "async0x42/Athene-V2-Chat-exl2_3.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/async0x42/Athene-V2-Chat-exl2_3.5bpw

SGLang

How to use async0x42/Athene-V2-Chat-exl2_3.5bpw 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 "async0x42/Athene-V2-Chat-exl2_3.5bpw" \
    --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": "async0x42/Athene-V2-Chat-exl2_3.5bpw",
		"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 "async0x42/Athene-V2-Chat-exl2_3.5bpw" \
        --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": "async0x42/Athene-V2-Chat-exl2_3.5bpw",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use async0x42/Athene-V2-Chat-exl2_3.5bpw with Docker Model Runner:
```
docker model run hf.co/async0x42/Athene-V2-Chat-exl2_3.5bpw
```

Configuration Parsing Warning:In config.json: "quantization_config.bits" must be an integer

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 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.

Downloads last month: 4

Model tree for async0x42/Athene-V2-Chat-exl2_3.5bpw

Base model

Qwen/Qwen2.5-72B

Finetuned

Qwen/Qwen2.5-72B-Instruct

Quantized

(85)

this model