Instructions to use rednote-hilab/dots.llm1.inst with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use rednote-hilab/dots.llm1.inst with Transformers:

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

pipe = pipeline("text-generation", model="rednote-hilab/dots.llm1.inst")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("rednote-hilab/dots.llm1.inst")
model = AutoModelForCausalLM.from_pretrained("rednote-hilab/dots.llm1.inst")
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 rednote-hilab/dots.llm1.inst with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "rednote-hilab/dots.llm1.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": "rednote-hilab/dots.llm1.inst",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/rednote-hilab/dots.llm1.inst

SGLang

How to use rednote-hilab/dots.llm1.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 "rednote-hilab/dots.llm1.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": "rednote-hilab/dots.llm1.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 "rednote-hilab/dots.llm1.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": "rednote-hilab/dots.llm1.inst",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use rednote-hilab/dots.llm1.inst with Docker Model Runner:
```
docker model run hf.co/rednote-hilab/dots.llm1.inst
```

Game-changer for 4x24GB setups! AWQ request

by hyunw55 - opened Jun 6, 2025

Discussion

hyunw55

Jun 6, 2025

If there's a 4-bit quantized version available - this is PERFECT for my 4x24GB setup! MoE architecture at this size is absolutely game-changing!
Huge thanks for this release - would love to see AWQ quantized versions if possible. That would make this model absolutely legendary for multi-GPU inference.
You guys rock! 🔥

djuna

Jun 6, 2025

How much context will you have as the model itself still use MHA?

gghfez

Jun 7, 2025

1GB per 1k context

shigureui

Jun 7, 2025

We need FP8 versions!

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