Instructions to use xx18/Baseline-4B-MATH12K with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xx18/Baseline-4B-MATH12K with Transformers:

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

pipe = pipeline("text-generation", model="xx18/Baseline-4B-MATH12K")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xx18/Baseline-4B-MATH12K")
model = AutoModelForCausalLM.from_pretrained("xx18/Baseline-4B-MATH12K", device_map="auto")
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 xx18/Baseline-4B-MATH12K with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xx18/Baseline-4B-MATH12K"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xx18/Baseline-4B-MATH12K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xx18/Baseline-4B-MATH12K

SGLang

How to use xx18/Baseline-4B-MATH12K 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 "xx18/Baseline-4B-MATH12K" \
    --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": "xx18/Baseline-4B-MATH12K",
		"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 "xx18/Baseline-4B-MATH12K" \
        --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": "xx18/Baseline-4B-MATH12K",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xx18/Baseline-4B-MATH12K with Docker Model Runner:
```
docker model run hf.co/xx18/Baseline-4B-MATH12K
```

Add model card for Composition-RL-8B

by nielsr HF Staff - opened Apr 23

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

+33

-0

nielsr

Apr 23

Hi! I'm Niels from the community science team at Hugging Face. I noticed this repository was missing a model card, so I'm opening this PR to add one.

This model card includes:

Metadata for pipeline_tag and library_name to ensure the model is correctly indexed.
Links to the Composition-RL paper and the official GitHub repository.
A summary of the training methodology and the model's lineage (initialized from Qwen3-8B-Base).
The BibTeX citation for attribution.

Let me know if you'd like to adjust any of the information!

Add model card for Composition-RL-8B02d9ae0e

xx18 changed pull request status to merged Apr 27

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment