Instructions to use SmallDoge/Doge-60M-checkpoint with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SmallDoge/Doge-60M-checkpoint with Transformers:

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

pipe = pipeline("text-generation", model="SmallDoge/Doge-60M-checkpoint", 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("SmallDoge/Doge-60M-checkpoint", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("SmallDoge/Doge-60M-checkpoint", 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 SmallDoge/Doge-60M-checkpoint with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SmallDoge/Doge-60M-checkpoint"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SmallDoge/Doge-60M-checkpoint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SmallDoge/Doge-60M-checkpoint

SGLang

How to use SmallDoge/Doge-60M-checkpoint 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 "SmallDoge/Doge-60M-checkpoint" \
    --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": "SmallDoge/Doge-60M-checkpoint",
		"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 "SmallDoge/Doge-60M-checkpoint" \
        --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": "SmallDoge/Doge-60M-checkpoint",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SmallDoge/Doge-60M-checkpoint with Docker Model Runner:
```
docker model run hf.co/SmallDoge/Doge-60M-checkpoint
```

Doge 60M checkpoint

Doge uses wsd_scheduler as the training scheduler, which divides the learning rate into three stages: warmup, stable, and decay. It allows us to continue training on any new dataset from any checkpoint in the stable stage without spikes of the training.

Here are the initial learning rates required to continue training at each checkpoint:

Doge-20M: 8e-3
Doge-60M: 6e-3
Doge-160M: 4e-3
Doge-320M: 2e-3

Model	Learning Rate	Schedule	Warmup Steps	Stable Steps
Doge-20M	8e-3	wsd_scheduler	800	6400
Doge-60M	6e-3	wsd_scheduler	1600	12800
Doge-160M	4e-3	wsd_scheduler	2400	19200
Doge-320M	2e-3	wsd_scheduler	3200	25600

Downloads last month: 15

Safetensors

Model size

54.6M params

Tensor type

F32

Dataset used to train SmallDoge/Doge-60M-checkpoint

Spaces using SmallDoge/Doge-60M-checkpoint 15

Collection including SmallDoge/Doge-60M-checkpoint

🐶Doge-CheckPoints

Collection

A series of checkPoint weights that can continue training on new datasets without spikes of the training. • 6 items • Updated Apr 21, 2025 • 2