Instructions to use pymlex/gemma3-1b-countdown-reasoning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pymlex/gemma3-1b-countdown-reasoning with Transformers:

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

pipe = pipeline("text-generation", model="pymlex/gemma3-1b-countdown-reasoning")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("pymlex/gemma3-1b-countdown-reasoning", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use pymlex/gemma3-1b-countdown-reasoning with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pymlex/gemma3-1b-countdown-reasoning"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pymlex/gemma3-1b-countdown-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pymlex/gemma3-1b-countdown-reasoning

SGLang

How to use pymlex/gemma3-1b-countdown-reasoning 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 "pymlex/gemma3-1b-countdown-reasoning" \
    --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": "pymlex/gemma3-1b-countdown-reasoning",
		"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 "pymlex/gemma3-1b-countdown-reasoning" \
        --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": "pymlex/gemma3-1b-countdown-reasoning",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pymlex/gemma3-1b-countdown-reasoning with Docker Model Runner:
```
docker model run hf.co/pymlex/gemma3-1b-countdown-reasoning
```

pymlex commited on 28 days ago

Commit

3f2b440

verified ·

1 Parent(s): 552da21

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -76,11 +76,10 @@ Validation accuracy gradually grows with small oscillations:
 ## Evaluation
-Validation was run on the first `1,000` examples of the validation split with batch size `200`.
-The final result is:
-- Validation accuracy: `0.8200` (`820/1000`)
 ## Inference

 ## Evaluation
+Validation was run on the first `1,000` examples of the validation split with batch size `200`. The validation accuracy is:
+- Original model: `0.1310` (`131/1000)
+- Reasoning fine-tuning: `0.82` (`820/1000`)
 ## Inference