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

Libraries

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

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

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

vLLM

How to use SmallDoge/Doge-60M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SmallDoge/Doge-60M"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

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

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

Update README.md

by JingzeShi - opened Dec 18, 2024

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+11

-6

Files changed (1) hide show

README.md +11 -6

README.md CHANGED Viewed

@@ -16,7 +16,6 @@ Doge is an ongoing research project where we aim to train a series of small lang
 In addition, Doge uses Dynamic Mask Attention as sequence transformation and can use Multi-Layer Perceptron or Cross Domain Mixture of Experts as state transformation. Dynamic Mask Attention allows the Transformer to use self-attention during training and state space during inference, and Cross Domain Mixture of Experts can directly inherit the weights of Multi-Layer Perceptron for further training. This model is trained by Jingze Shi, it only allows text input and text generation, for detailed algorithm and model architecture, please refer to [Wonderful Matrices](https://arxiv.org/abs/2412.11834), the ongoing research repository is [Wonderful Matrices](https://github.com/LoserCheems/WonderfulMatrices).
 ## Uses
 ```python
@@ -37,18 +36,24 @@ In addition, Doge uses Dynamic Mask Attention as sequence transformation and can
 > TODO: The larger model is under training and will be uploaded soon.
-|| Training Data | Epochs | Steps | Content Length | Tokens | LR | Batch Size | Precision |
 |---|---|---|---|---|---|---|---|---|
-| [Doge-20M](https://huggingface.co/LoserCheems/Doge-20M) | [HuggingFaceTB/smollm-corpus](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus) | 2 | 10k | 2048 | 5B | 8e-4 | 0.25M | bfloat16 |
-| [Doge-60M](https://huggingface.co/LoserCheems/Doge-60M) | [HuggingFaceTB/smollm-corpus](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus) | 2 | 20k | 2048 | 20B | 6e-4 | 0.5M | bfloat16 |
-**Training Environment**:
 - Image: nvcr.io/nvidia/pytorch:24.10-py3
 - Hardware: 1x NVIDIA RTX 4090
 - Software: Transformers
 ## Citation
 ```bibtex

 In addition, Doge uses Dynamic Mask Attention as sequence transformation and can use Multi-Layer Perceptron or Cross Domain Mixture of Experts as state transformation. Dynamic Mask Attention allows the Transformer to use self-attention during training and state space during inference, and Cross Domain Mixture of Experts can directly inherit the weights of Multi-Layer Perceptron for further training. This model is trained by Jingze Shi, it only allows text input and text generation, for detailed algorithm and model architecture, please refer to [Wonderful Matrices](https://arxiv.org/abs/2412.11834), the ongoing research repository is [Wonderful Matrices](https://github.com/LoserCheems/WonderfulMatrices).
 ## Uses
 ```python
 > TODO: The larger model is under training and will be uploaded soon.
+**Training**:
+| Model | Training Data | Epochs | Steps | Content Length | Tokens | LR | Batch Size | Precision |
 |---|---|---|---|---|---|---|---|---|
+| [Doge-20M](https://huggingface.co/JingzeShi/Doge-20M) | [HuggingFaceTB/smollm-corpus](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus) | 2 | 10k | 2048 | 5B | 8e-4 | 0.25M | bfloat16 |
+| [Doge-60M](https://huggingface.co/JingzeShi/Doge-60M) | [HuggingFaceTB/smollm-corpus](https://huggingface.co/datasets/HuggingFaceTB/smollm-corpus) | 2 | 20k | 2048 | 20B | 6e-4 | 0.5M | bfloat16 |
+**Evaluation**:
+| Model | TriviaQA | MMLU | ARC | PIQA | HellaSwag | OBQA | Winogrande |
+|---|---|---|---|---|---|---|---|
+| [Doge-20M](https://huggingface.co/JingzeShi/Doge-20M) | - | 26.01 | 36.15 | 56.26 | 26.60 | 26.60 | 50.12 |
+| [Doge-60M](https://huggingface.co/JingzeShi/Doge-60M) | - | 25.81 | 45.49 | 61.37 | 29.65 | 27.40 | 52.57 |
+**Environment**:
 - Image: nvcr.io/nvidia/pytorch:24.10-py3
 - Hardware: 1x NVIDIA RTX 4090
 - Software: Transformers
 ## Citation
 ```bibtex