Instructions to use meituan/DeepSeek-R1-Channel-INT8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use meituan/DeepSeek-R1-Channel-INT8 with Transformers:

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

pipe = pipeline("text-generation", model="meituan/DeepSeek-R1-Channel-INT8", 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("meituan/DeepSeek-R1-Channel-INT8", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("meituan/DeepSeek-R1-Channel-INT8", 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 meituan/DeepSeek-R1-Channel-INT8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "meituan/DeepSeek-R1-Channel-INT8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "meituan/DeepSeek-R1-Channel-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/meituan/DeepSeek-R1-Channel-INT8

SGLang

How to use meituan/DeepSeek-R1-Channel-INT8 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 "meituan/DeepSeek-R1-Channel-INT8" \
    --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": "meituan/DeepSeek-R1-Channel-INT8",
		"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 "meituan/DeepSeek-R1-Channel-INT8" \
        --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": "meituan/DeepSeek-R1-Channel-INT8",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use meituan/DeepSeek-R1-Channel-INT8 with Docker Model Runner:
```
docker model run hf.co/meituan/DeepSeek-R1-Channel-INT8
```

pkumc commited on Feb 26, 2025

Commit

0e4c3b5

verified ·

1 Parent(s): 77ddaef

Add files using upload-large-folder tool

Browse files

Files changed (12) hide show

.gitattributes +1 -0
figures/benchmark.jpg +3 -0
model-00025-of-000163.safetensors +3 -0
model-00028-of-000163.safetensors +3 -0
model-00069-of-000163.safetensors +3 -0
model-00075-of-000163.safetensors +3 -0
model-00077-of-000163.safetensors +3 -0
model-00080-of-000163.safetensors +3 -0
model-00114-of-000163.safetensors +3 -0
model-00143-of-000163.safetensors +3 -0
model-00155-of-000163.safetensors +3 -0
model-00158-of-000163.safetensors +3 -0

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+figures/benchmark.jpg filter=lfs diff=lfs merge=lfs -text

meituan
/

DeepSeek-R1-Channel-INT8

Add files using upload-large-folder tool

Git LFS Details

+version https://git-lfs.github.com/spec/v1
+oid sha256:1e839ab0831f5de270c43ab662ce07b8e49ed3c762321b8320ecacad18a9dd30
+size 4305738040

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd994f4b9901f386966a562da803fc300e77007910dea3f6a291439e248b8833
+size 4305717552

+version https://git-lfs.github.com/spec/v1
+oid sha256:a098b130f90e131888ccd7e1765407cd9a6ca1b7d3d3e120332a76482be85c9e
+size 4305782864

+version https://git-lfs.github.com/spec/v1
+oid sha256:a2046b5b2a5252aae080703a4d416e7542f757b2bb04dcdae3038302bc6412c2
+size 4305738048

+version https://git-lfs.github.com/spec/v1
+oid sha256:6a337ef88bfc46a097ed380b07709d0cbc13687d9f096314189bce12c9520153
+size 4305737984

+version https://git-lfs.github.com/spec/v1
+oid sha256:59d9866831544e9d33752dd0f0538d6a683c0be1a3378677c9267d89bdfc3cd9
+size 4305762168

+version https://git-lfs.github.com/spec/v1
+oid sha256:699a425f511e515e47d71fa905a0d19d4a776c8c6a9d19bbe8856c51daa09fc9
+size 4305782464

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@