Instructions to use RabotniKuma/Fast-Math-R1-14B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RabotniKuma/Fast-Math-R1-14B with Transformers:

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

pipe = pipeline("text-generation", model="RabotniKuma/Fast-Math-R1-14B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RabotniKuma/Fast-Math-R1-14B")
model = AutoModelForCausalLM.from_pretrained("RabotniKuma/Fast-Math-R1-14B")
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 RabotniKuma/Fast-Math-R1-14B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RabotniKuma/Fast-Math-R1-14B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RabotniKuma/Fast-Math-R1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RabotniKuma/Fast-Math-R1-14B

SGLang

How to use RabotniKuma/Fast-Math-R1-14B 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 "RabotniKuma/Fast-Math-R1-14B" \
    --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": "RabotniKuma/Fast-Math-R1-14B",
		"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 "RabotniKuma/Fast-Math-R1-14B" \
        --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": "RabotniKuma/Fast-Math-R1-14B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RabotniKuma/Fast-Math-R1-14B with Docker Model Runner:
```
docker model run hf.co/RabotniKuma/Fast-Math-R1-14B
```

RabotniKuma commited on Apr 17, 2025

Commit

cc6b91b

verified ·

1 Parent(s): d495492

Update README.md

Browse files

Files changed (1) hide show

README.md +10 -8

README.md CHANGED Viewed

@@ -12,25 +12,27 @@ base_model:
 # Summary
 By applying SFT and GRPO on difficult math problems, we enhanced the performance of `DeepSeek-R1-Distill-Qwen-14B` and developed `Fast-Math-R1-14B`,
-which achieves up to 60% faster inference while maintaining accuracy.
 Technical details can be found in [Kaggle Discussion](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2/discussion/571252) and [Github](https://github.com/analokmaus/kaggle-aimo2-fast-math-r1).
-<img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1973217%2F2bebc2bf743e7fe92f9e1fa9527220fc%2Fpass1_aime_answers_only.png?generation=1744851657610346&alt=media" max-height="300px">
 <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1973217%2F4f221ab914f3e950fa35bdab5723d462%2Fpass1_aime_all.png?generation=1744851665782759&alt=media" max-height="300px">
 |                              |              | AIME 2024        |               | AIME 2025        |               |
 | ---------------------------- | ------------ | ---------------- | ------------- | ---------------- | ------------- |
 | Model                        | Token budget | Pass@1 (avg. 64) | Output tokens | Pass@1 (avg. 64) | Output tokens |
 | DeepSeek-R1-Distill-Qwen-14B | 16384        | 63.3             | 9590          | 46.7             | 10602         |
-|                              | 12800        | 58               | 6444          | 41.9             | 6684          |
-|                              | 8192         | 45.6             | 4920          | 30.6             | 4611          |
 | Light-R1-14B-DS              | 16384        | **66.8**             | 10146         | **51.3**             | 11308         |
-|                              | 12800        | 59.2             | 6974          | 43.8             | 6869          |
-|                              | 8192         | 42.4             | 5500          | 30.4             | 4908          |
 | Fast-Math-R1-14B             | 16384        | 66               | **7932**          | 49.2             | **9066**          |
-|                              | 12800        | **63**               | **5996**          | **46.1**             | **6127**          |
-|                              | 8192         | **51.4**             | **4269**          | **37.2**             | **3905**          |
 # Dataset

 # Summary
 By applying SFT and GRPO on difficult math problems, we enhanced the performance of `DeepSeek-R1-Distill-Qwen-14B` and developed `Fast-Math-R1-14B`,
+which achieves up to 60% (on average approx. 30%) faster inference while maintaining accuracy.
 Technical details can be found in [Kaggle Discussion](https://www.kaggle.com/competitions/ai-mathematical-olympiad-progress-prize-2/discussion/571252) and [Github](https://github.com/analokmaus/kaggle-aimo2-fast-math-r1).
 <img src="https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F1973217%2F4f221ab914f3e950fa35bdab5723d462%2Fpass1_aime_all.png?generation=1744851665782759&alt=media" max-height="300px">
 |                              |              | AIME 2024        |               | AIME 2025        |               |
 | ---------------------------- | ------------ | ---------------- | ------------- | ---------------- | ------------- |
 | Model                        | Token budget | Pass@1 (avg. 64) | Output tokens | Pass@1 (avg. 64) | Output tokens |
 | DeepSeek-R1-Distill-Qwen-14B | 16384        | 63.3             | 9590          | 46.7             | 10602         |
+|                              | 12800        | 58               | 8632          | 41.9             | 9363          |
+|                              | 8192         | 45.6             | 6638          | 30.6             | 6897          |
 | Light-R1-14B-DS              | 16384        | **66.8**             | 10146         | **51.3**             | 11308         |
+|                              | 12800        | 59.2             | 9110          | 43.8             | 9834          |
+|                              | 8192         | 42.4             | 7020          | 30.4             | 7124          |
 | Fast-Math-R1-14B             | 16384        | 66               | **7932**          | 49.2             | **9066**          |
+|                              | 12800        | **63**               | **7449**          | **46.1**             | **8282**          |
+|                              | 8192         | **51.4**             | **5963**          | **37.2**             | **6256**          |
+| Fast-Math-R1-14B-SFT Only    | 16384        | 65.2             | 10268         | 49.7             | 11264         |
+|                              | 12800        | 57.2             | 9180          | 42.8             | 9805          |
+|                              | 8192         | 41.3             | 7015          | 30.1             | 7074          |
 # Dataset