Instructions to use dots-studio/dots.llm1.inst-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dots-studio/dots.llm1.inst-FP8-dynamic with Transformers:

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

pipe = pipeline("text-generation", model="dots-studio/dots.llm1.inst-FP8-dynamic")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dots-studio/dots.llm1.inst-FP8-dynamic")
model = AutoModelForCausalLM.from_pretrained("dots-studio/dots.llm1.inst-FP8-dynamic", 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 dots-studio/dots.llm1.inst-FP8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dots-studio/dots.llm1.inst-FP8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dots-studio/dots.llm1.inst-FP8-dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dots-studio/dots.llm1.inst-FP8-dynamic

SGLang

How to use dots-studio/dots.llm1.inst-FP8-dynamic 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 "dots-studio/dots.llm1.inst-FP8-dynamic" \
    --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": "dots-studio/dots.llm1.inst-FP8-dynamic",
		"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 "dots-studio/dots.llm1.inst-FP8-dynamic" \
        --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": "dots-studio/dots.llm1.inst-FP8-dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dots-studio/dots.llm1.inst-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/dots-studio/dots.llm1.inst-FP8-dynamic
```

redmoe-ai-v1 commited on Jun 23, 2025

Commit

0b22634

verified ·

1 Parent(s): 3d547ab

Upload folder using huggingface_hub

Browse files

Files changed (7) hide show

.gitattributes +3 -0
README.md +3 -3
figures/XHSlong750px.png +0 -0
figures/new_logo.png +3 -0
figures/new_logo2.png +0 -0
figures/performance.png +3 -0
figures/wechat.png +3 -0

.gitattributes CHANGED Viewed

@@ -34,3 +34,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text

 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+figures/new_logo.png filter=lfs diff=lfs merge=lfs -text
+figures/performance.png filter=lfs diff=lfs merge=lfs -text
+figures/wechat.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -66,11 +66,11 @@ The highlights from `dots.llm1` include:
 ## 3. dots.llm1.inst.FP8-dynamic
-### Docker (vllm)
 We release the quantized `dots.llm1.inst.FP8-dynamic` model, which retains approximately 98% of the original performance after quantization.
-run vllm inference using docker `rednote-hilab/vllm-openai-v0.9.1`. The docker images are available on [Docker Hub](https://hub.docker.com/repository/docker/rednotehilab/dots1/tags), based on the official images.
 ```bash
 python3 -m vllm.entrypoints.openai.api_server --model rednote-hilab/dots.llm1.inst.FP8-dynamic --tensor-parallel-size 4 --pipeline-parallel-size 1 --trust-remote-code --served-model-name dots1

 ## 3. dots.llm1.inst.FP8-dynamic
 We release the quantized `dots.llm1.inst.FP8-dynamic` model, which retains approximately 98% of the original performance after quantization.
+### Docker (vllm)
+For convenience, we recommend running vLLM inference using our Docker image `rednote-hilab/vllm-openai-v0.9.1`, , which is available on [Docker Hub](https://hub.docker.com/repository/docker/rednotehilab/dots1/tags).
 ```bash
 python3 -m vllm.entrypoints.openai.api_server --model rednote-hilab/dots.llm1.inst.FP8-dynamic --tensor-parallel-size 4 --pipeline-parallel-size 1 --trust-remote-code --served-model-name dots1

figures/XHSlong750px.png ADDED Viewed

figures/new_logo.png ADDED Viewed

Git LFS Details

SHA256: 2e5808698bcd60df90869af469743248a4560d0ffb2232eceb74cd9c0a7df763
Pointer size: 131 Bytes
Size of remote file: 101 kB

figures/new_logo2.png ADDED Viewed

figures/performance.png ADDED Viewed

Git LFS Details

SHA256: ca42a057f65c1ea12c303e41938dbe38fc285769002272af767b76605cf8ea98
Pointer size: 131 Bytes
Size of remote file: 139 kB

figures/wechat.png ADDED Viewed

Git LFS Details

SHA256: e6f386b64bd313bd998bf0f25e9f1b32c0fbbfe7d972a60227c22fdc044da885
Pointer size: 131 Bytes
Size of remote file: 118 kB