Instructions to use OpenResearcher/OpenResearcher-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenResearcher/OpenResearcher-30B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="OpenResearcher/OpenResearcher-30B-A3B", trust_remote_code=True)
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("OpenResearcher/OpenResearcher-30B-A3B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("OpenResearcher/OpenResearcher-30B-A3B", trust_remote_code=True, 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OpenResearcher/OpenResearcher-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenResearcher/OpenResearcher-30B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenResearcher/OpenResearcher-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/OpenResearcher/OpenResearcher-30B-A3B

SGLang

How to use OpenResearcher/OpenResearcher-30B-A3B 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 "OpenResearcher/OpenResearcher-30B-A3B" \
    --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": "OpenResearcher/OpenResearcher-30B-A3B",
		"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 "OpenResearcher/OpenResearcher-30B-A3B" \
        --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": "OpenResearcher/OpenResearcher-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OpenResearcher/OpenResearcher-30B-A3B with Docker Model Runner:
```
docker model run hf.co/OpenResearcher/OpenResearcher-30B-A3B
```

OpenResearcher-30B-A3B

Commit History

Mar 24

11:02
Update model card: add pipeline tag, paper link, and sample usage⁠

nielsr HF Staff

Verified signature
73a9013

Feb 23

20:46
Update README.md

ZhuofengLi

Verified signature
a24e74b

Feb 22

01:47
Upload main-table.png

IPF

Verified signature
d75894e

Feb 17

13:08
Adding `transformers` as the library name (#3)⁠

ZhuofengLi +1: ariG23498

d7a84d1

Feb 15

00:52
Upload teaser.png

IPF

Verified signature
7613a47

Feb 12

22:22
Upload teaser.png

IPF

Verified signature
3796539
15:59
Update README.md

ZhuofengLi

Verified signature
9e48b6d
15:59
Update README.md

ZhuofengLi

Verified signature
2288cee

Feb 11

21:16
Update README.md

ZhuofengLi

Verified signature
99e916e
20:40
Update README.md

ZhuofengLi

Verified signature
ac1a8ea
20:03
Update README.md

ZhuofengLi

Verified signature
abeb0bb

Feb 9

15:45
Update README.md

ZhuofengLi

Verified signature
a635da5
15:43
Update README.md

ZhuofengLi

Verified signature
032d571
15:34
Update README.md

ZhuofengLi

Verified signature
778bac6
15:33
Upload wechat_group.jpg

ZhuofengLi

Verified signature
6dc1970

Feb 8

11:26
Update README.md

ZhuofengLi

Verified signature
96184dd

Feb 7

19:44
Update README.md

ZhuofengLi

Verified signature
14af96b

Feb 6

14:55
Update README.md

ZhuofengLi

Verified signature
9ef36aa
14:54
Update README.md

ZhuofengLi

Verified signature
04e64e4
14:52
Update README.md

ZhuofengLi

Verified signature
9af4e87
14:49
Update README.md

ZhuofengLi

Verified signature
e9f33f9
13:24
Update README.md

ZhuofengLi

Verified signature
78b0924
13:23
Delete imgs/eval.svg

ZhuofengLi

Verified signature
6da7096
13:23
Upload eval.png

ZhuofengLi

Verified signature
2a3e284
13:20
Upload 2 files

ZhuofengLi

Verified signature
f7fedc2
13:19
Update README.md

ZhuofengLi

Verified signature
310c4c4

Feb 5

22:14
Upload teaser.png

IPF

Verified signature
060a67f
21:23
Update README.md

ZhuofengLi

Verified signature
4dbb4c7

Feb 3

23:28
Update README.md

ZhuofengLi

Verified signature
4ce1b07
23:17
Update README.md

ZhuofengLi

Verified signature
dc8f587
23:15
Update README.md

ZhuofengLi

Verified signature
09453ad
23:13
Update README.md

ZhuofengLi

Verified signature
159de89
23:12
Update README.md

ZhuofengLi

Verified signature
367bfc5
23:12
Create README.md

ZhuofengLi

Verified signature
3644eb3
22:53
Upload 9 files

ZhuofengLi

Verified signature
164ad38
16:38
Upload folder using huggingface_hub

ZhuofengLi

Verified signature
f8b22df
16:28
initial commit

ZhuofengLi

Verified signature
a5b37f4

Commit History

Mar 24

Update model card: add pipeline tag, paper link, and sample usage⁠

Feb 23

Update README.md

Feb 22

Upload main-table.png

Feb 17

Adding `transformers` as the library name (#3)⁠

Feb 15

Upload teaser.png

Feb 12

Upload teaser.png

Update README.md

Update README.md

Feb 11

Update README.md

Update README.md

Update README.md

Feb 9

Update README.md

Update README.md

Update README.md

Upload wechat_group.jpg

Feb 8

Update README.md

Feb 7

Update README.md

Feb 6

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Delete imgs/eval.svg

Upload eval.png

Upload 2 files

Update README.md

Feb 5

Upload teaser.png

Update README.md

Feb 3

Update README.md

Update README.md

Update README.md

Update README.md

Update README.md

Create README.md

Upload 9 files

Upload folder using huggingface_hub

initial commit