Instructions to use inclusionAI/GroveMoE-Inst with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use inclusionAI/GroveMoE-Inst with Transformers:

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

pipe = pipeline("text-generation", model="inclusionAI/GroveMoE-Inst", 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("inclusionAI/GroveMoE-Inst", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("inclusionAI/GroveMoE-Inst", trust_remote_code=True)
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

vLLM

How to use inclusionAI/GroveMoE-Inst with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/inclusionAI/GroveMoE-Inst

SGLang

How to use inclusionAI/GroveMoE-Inst 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 "inclusionAI/GroveMoE-Inst" \
    --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": "inclusionAI/GroveMoE-Inst",
		"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 "inclusionAI/GroveMoE-Inst" \
        --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": "inclusionAI/GroveMoE-Inst",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use inclusionAI/GroveMoE-Inst with Docker Model Runner:
```
docker model run hf.co/inclusionAI/GroveMoE-Inst
```

`expert_bias`

by J22 - opened Sep 7, 2025

Discussion

J22

Sep 7, 2025

why expert_bias is not used?

https://huggingface.co/inclusionAI/GroveMoE-Inst/blob/main/modeling_grove_moe.py#L303

HaoxingChen

inclusionAI org Sep 8, 2025

•

edited Sep 8, 2025

Hello. The expert_bias is used only during training, as you can see in the code below.

router_logits = self.gate(hidden_states)
routing_weights = F.softmax(router_logits, dim=-1, dtype=torch.float)
bias_routing_weights = torch.sigmoid(router_logits).to(torch.float)

if self.training:
       bias_routing_weights = bias_routing_weights + self.expert_bias.to(routing_weights.device)
else:
       bias_routing_weights = bias_routing_weights

_, selected_experts = torch.topk(bias_routing_weights, self.top_k, dim=-1)

During inference, we allow for a bias because real-world data distributions are not uniform. This approach produces better results than forcibly averaging the outputs. Furthermore, the bias obtained from the final pre-training step is not guaranteed to balance the model for a new inference distribution.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment