Instructions to use amd/Instella-MoE-16B-A3B-Pretrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use amd/Instella-MoE-16B-A3B-Pretrain with Transformers:

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

pipe = pipeline("text-generation", model="amd/Instella-MoE-16B-A3B-Pretrain", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("amd/Instella-MoE-16B-A3B-Pretrain", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("amd/Instella-MoE-16B-A3B-Pretrain", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use amd/Instella-MoE-16B-A3B-Pretrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "amd/Instella-MoE-16B-A3B-Pretrain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "amd/Instella-MoE-16B-A3B-Pretrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/amd/Instella-MoE-16B-A3B-Pretrain

SGLang

How to use amd/Instella-MoE-16B-A3B-Pretrain 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 "amd/Instella-MoE-16B-A3B-Pretrain" \
    --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": "amd/Instella-MoE-16B-A3B-Pretrain",
		"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 "amd/Instella-MoE-16B-A3B-Pretrain" \
        --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": "amd/Instella-MoE-16B-A3B-Pretrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use amd/Instella-MoE-16B-A3B-Pretrain with Docker Model Runner:
```
docker model run hf.co/amd/Instella-MoE-16B-A3B-Pretrain
```

Instella-MoE-16B-A3B-Pretrain

Commit History

Update README.md with arxiv paper

b56eb27

Yonatan Dukler commited on 17 days ago

update modeling code for transformers 4.57-5+ compatibility

2f08170

Yonatan Dukler commited on 29 days ago

Release Instella-MoE-16B-A3B-Pretrain

838fd2b
verified

Prakamya commited on Jul 24

Release Instella-MoE-16B-A3B-Pretrain

b2632fa
verified

Prakamya commited on Jul 23

initial commit

b991fdc
verified

Prakamya commited on Jul 23

Commit History

Update README.md with arxiv paper b56eb27

update modeling code for transformers 4.57-5+ compatibility 2f08170

Release Instella-MoE-16B-A3B-Pretrain 838fd2b verified

Release Instella-MoE-16B-A3B-Pretrain b2632fa verified

initial commit b991fdc verified

Update README.md with arxiv paper

b56eb27

update modeling code for transformers 4.57-5+ compatibility

2f08170

Release Instella-MoE-16B-A3B-Pretrain

838fd2b
verified

Release Instella-MoE-16B-A3B-Pretrain

b2632fa
verified

initial commit

b991fdc
verified