Instructions to use Orion-zhen/athene-70b-4.5bpw-exl2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Orion-zhen/athene-70b-4.5bpw-exl2 with Transformers:

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

pipe = pipeline("text-generation", model="Orion-zhen/athene-70b-4.5bpw-exl2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("Orion-zhen/athene-70b-4.5bpw-exl2")
model = AutoModelForMultimodalLM.from_pretrained("Orion-zhen/athene-70b-4.5bpw-exl2")
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 Orion-zhen/athene-70b-4.5bpw-exl2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Orion-zhen/athene-70b-4.5bpw-exl2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Orion-zhen/athene-70b-4.5bpw-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Orion-zhen/athene-70b-4.5bpw-exl2

SGLang

How to use Orion-zhen/athene-70b-4.5bpw-exl2 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 "Orion-zhen/athene-70b-4.5bpw-exl2" \
    --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": "Orion-zhen/athene-70b-4.5bpw-exl2",
		"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 "Orion-zhen/athene-70b-4.5bpw-exl2" \
        --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": "Orion-zhen/athene-70b-4.5bpw-exl2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Orion-zhen/athene-70b-4.5bpw-exl2 with Docker Model Runner:
```
docker model run hf.co/Orion-zhen/athene-70b-4.5bpw-exl2
```

Orion commited on Aug 9, 2024

Commit

28357ef

1 Parent(s): a4b01e1

add: model files

Browse files

Files changed (5) hide show

output-00001-of-00005.safetensors +3 -0
output-00002-of-00005.safetensors +3 -0
output-00003-of-00005.safetensors +3 -0
output-00004-of-00005.safetensors +3 -0
output-00005-of-00005.safetensors +3 -0

output-00001-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:6838d217e1d167852d30565134b7a395f733736711c1f2e8bdd21c6539e4d3e0
+size 8492848242

output-00002-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:987cc4876699e02d08fb04e5b1ad16f1bd089cb2e7ab36134698dc9c41c16707
+size 8550076588

output-00003-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:11ca745bdc428d5312cb84a99177fdaa662408fc3104c346cd04d90d46b9ecb5
+size 8586348968

output-00004-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f38494499c52a083cf911a84f65d18ea21486481c5c6e412dfa7e1ab73ca7cc9
+size 8545117528

output-00005-of-00005.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd98a6c80d33937a6e966b4a27e6764b22aa8cc431ef4b0b179a3734d613d05
+size 7487295500