Instructions to use SmallDoge/Doge-20M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SmallDoge/Doge-20M with Transformers:

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

pipe = pipeline("text-generation", model="SmallDoge/Doge-20M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SmallDoge/Doge-20M")
model = AutoModelForCausalLM.from_pretrained("SmallDoge/Doge-20M")
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-20M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SmallDoge/Doge-20M"
# 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-20M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SmallDoge/Doge-20M

SGLang

How to use SmallDoge/Doge-20M 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-20M" \
    --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-20M",
		"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-20M" \
        --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-20M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SmallDoge/Doge-20M with Docker Model Runner:
```
docker model run hf.co/SmallDoge/Doge-20M
```

JingzeShi commited on Feb 3, 2025

Commit

45f6931

verified ·

1 Parent(s): 363c52a

Upload tokenizer

Browse files

Files changed (2) hide show

tokenizer.json +8 -8
tokenizer_config.json +8 -8

tokenizer.json CHANGED Viewed

@@ -2272,8 +2272,8 @@
       "special": true
     },
     {
-      "id": 252,
-      "content": "<|reserved_special_token_244|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2281,8 +2281,8 @@
       "special": true
     },
     {
-      "id": 253,
-      "content": "<|reserved_special_token_245|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2290,8 +2290,8 @@
       "special": true
     },
     {
-      "id": 254,
-      "content": "<|reserved_special_token_246|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
@@ -2299,8 +2299,8 @@
       "special": true
     },
     {
-      "id": 255,
-      "content": "<|reserved_special_token_247|>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

       "special": true
     },
     {
+      "id": 32768,
+      "content": "<think>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
       "special": true
     },
     {
+      "id": 32769,
+      "content": "</think>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
       "special": true
     },
     {
+      "id": 32770,
+      "content": "<answer>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,
       "special": true
     },
     {
+      "id": 32771,
+      "content": "</answer>",
       "single_word": false,
       "lstrip": false,
       "rstrip": false,

tokenizer_config.json CHANGED Viewed

@@ -2016,32 +2016,32 @@
       "single_word": false,
       "special": true
     },
-    "252": {
-      "content": "<|reserved_special_token_244|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "253": {
-      "content": "<|reserved_special_token_245|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "254": {
-      "content": "<|reserved_special_token_246|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "255": {
-      "content": "<|reserved_special_token_247|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,

       "single_word": false,
       "special": true
     },
+    "32768": {
+      "content": "<think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "32769": {
+      "content": "</think>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "32770": {
+      "content": "<answer>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
+    "32771": {
+      "content": "</answer>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,