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

Libraries

How to use BuckalewFinancial/DeepSeek-R1 with Transformers:

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

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

Install from pip and serve model

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

Use Docker

docker model run hf.co/BuckalewFinancial/DeepSeek-R1

SGLang

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

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

BuckalewFinancial commited on Jan 29, 2025

Commit

7b97d81

verified ·

1 Parent(s): e308fe9

downloads

Browse files

Files changed (6) hide show

COMMIT_EDITMSG +1 -0
HEAD +1 -0
config +24 -0
description +1 -0
index +0 -0
packed-refs +2 -0

COMMIT_EDITMSG ADDED Viewed

	@@ -0,0 +1 @@


1	+ Partial upload due to storage constraints

HEAD ADDED Viewed

	@@ -0,0 +1 @@


1	+ ref: refs/heads/main

config ADDED Viewed

	@@ -0,0 +1,24 @@

+[core]
+	repositoryformatversion = 0
+	filemode = false
+	bare = false
+	logallrefupdates = true
+	symlinks = false
+	ignorecase = true
+[remote "origin"]
+	url = https://huggingface.co/deepseek-ai/DeepSeek-R1
+	fetch = +refs/heads/*:refs/remotes/origin/*
+[branch "main"]
+	remote = origin
+	merge = refs/heads/main
+[lfs]
+	repositoryformatversion = 0
+[remote "my_repo"]
+	url = https://huggingface.co/BuckalewFinancial/DeepSeek-R1
+	fetch = +refs/heads/*:refs/remotes/my_repo/*
+[lfs "https://huggingface.co/BuckalewFinancial/DeepSeek-R1.git/info/lfs"]
+	locksverify = false
+	access = basic
+[lfs "customtransfer.multipart"]
+	path = huggingface-cli
+	args = lfs-multipart-upload

description ADDED Viewed

	@@ -0,0 +1 @@


1	+ Unnamed repository; edit this file 'description' to name the repository.

index ADDED Viewed

Binary file (1.02 kB). View file

packed-refs ADDED Viewed

	@@ -0,0 +1,2 @@


1	+ # pack-refs with: peeled fully-peeled sorted
2	+ 5dde110d1a9ee857b90a6710b7138f9130ce6fa0 refs/remotes/origin/main