Instructions to use ulab-ai/Time-R1-Theta1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ulab-ai/Time-R1-Theta1 with Transformers:

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

pipe = pipeline("text-generation", model="ulab-ai/Time-R1-Theta1")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ulab-ai/Time-R1-Theta1")
model = AutoModelForCausalLM.from_pretrained("ulab-ai/Time-R1-Theta1")
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 ulab-ai/Time-R1-Theta1 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ulab-ai/Time-R1-Theta1"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ulab-ai/Time-R1-Theta1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ulab-ai/Time-R1-Theta1

SGLang

How to use ulab-ai/Time-R1-Theta1 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 "ulab-ai/Time-R1-Theta1" \
    --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": "ulab-ai/Time-R1-Theta1",
		"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 "ulab-ai/Time-R1-Theta1" \
        --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": "ulab-ai/Time-R1-Theta1",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ulab-ai/Time-R1-Theta1 with Docker Model Runner:
```
docker model run hf.co/ulab-ai/Time-R1-Theta1
```

nielsr HF Staff commited on Jun 3, 2025

Commit

ff2ea47

verified ·

1 Parent(s): eac3305

Replace Arxiv paper link with Hugging Face paper link

Browse files

This PR replaces the arXiv paper link with the Hugging Face Papers link for improved accessibility and discoverability of the paper associated with this model.

Files changed (1) hide show

README.md +7 -6

README.md CHANGED Viewed

@@ -3,15 +3,15 @@ base_model:
 - Qwen/Qwen2.5-3B-Instruct
 datasets:
 - ulab-ai/Time-Bench
 license: apache-2.0
 tags:
 - temporal-reasoning
 - reinforcement-learning
 - large-language-models
 paperswithcode:
   arxiv_id: 2505.13508
-library_name: transformers
-pipeline_tag: text-generation
 ---
 <center>
@@ -19,12 +19,12 @@ pipeline_tag: text-generation
 </center>
 <div align="center">
-<a href="https://huggingface.co/datasets/ulab-ai/Time-Bench"> 📊 <strong>Dataset</strong></a> | <a href="https://github.com/ulab-uiuc/Time-R1">🚀 <strong>Code</strong></a> | <a href="https://arxiv.org/abs/2505.13508">📖 <strong>Paper</strong></a>
 </div>
 # Time-R1 Model Series
-This collection hosts the official checkpoints for the **Time-R1** model, as described in the paper "Time-R1: Towards Comprehensive Temporal Reasoning in LLMs". Time-R1 is a 3B parameter Large Language Model trained with a novel three-stage reinforcement learning curriculum to endow it with comprehensive temporal abilities: understanding, prediction, and creative generation.
 These models are trained using the [Time-Bench dataset](https://huggingface.co/datasets/ulab-ai/Time-Bench).
@@ -52,7 +52,7 @@ This model builds upon Stage 1 capabilities to predict future event timings.
 * **[Time-R1-Theta2](https://huggingface.co/ulab-ai/Time-R1-Theta2):** Checkpoint θ₂, after Stage 2 training.
    * *Focus: Predicting the timing of future events occurring after its initial knowledge cutoff.*
-Please refer to the [main paper](https://arxiv.org/abs/2505.13508) for detailed discussions on the architecture, training methodology, and comprehensive evaluations.
 ## How to Use
@@ -76,4 +76,5 @@ model = AutoModelForCausalLM.from_pretrained(model_name)
   author={Liu, Zijia and Han, Peixuan and Yu, Haofei and Li, Haoru and You, Jiaxuan},
   journal={arXiv preprint arXiv:2505.13508},
   year={2025}
-}

 - Qwen/Qwen2.5-3B-Instruct
 datasets:
 - ulab-ai/Time-Bench
+library_name: transformers
 license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - temporal-reasoning
 - reinforcement-learning
 - large-language-models
 paperswithcode:
   arxiv_id: 2505.13508
 ---
 <center>
 </center>
 <div align="center">
+<a href="https://huggingface.co/datasets/ulab-ai/Time-Bench"> 📊 <strong>Dataset</strong></a> | <a href="https://github.com/ulab-uiuc/Time-R1">🚀 <strong>Code</strong></a> | <a href="https://huggingface.co/papers/2505.13508">📖 <strong>Paper</strong></a>
 </div>
 # Time-R1 Model Series
+This collection hosts the official checkpoints for the **Time-R1** model, as described in the paper [Time-R1: Towards Comprehensive Temporal Reasoning in LLMs](https://huggingface.co/papers/2505.13508). Time-R1 is a 3B parameter Large Language Model trained with a novel three-stage reinforcement learning curriculum to endow it with comprehensive temporal abilities: understanding, prediction, and creative generation.
 These models are trained using the [Time-Bench dataset](https://huggingface.co/datasets/ulab-ai/Time-Bench).
 * **[Time-R1-Theta2](https://huggingface.co/ulab-ai/Time-R1-Theta2):** Checkpoint θ₂, after Stage 2 training.
    * *Focus: Predicting the timing of future events occurring after its initial knowledge cutoff.*
+Please refer to the [main paper](https://huggingface.co/papers/2505.13508) for detailed discussions on the architecture, training methodology, and comprehensive evaluations.
 ## How to Use
   author={Liu, Zijia and Han, Peixuan and Yu, Haofei and Li, Haoru and You, Jiaxuan},
   journal={arXiv preprint arXiv:2505.13508},
   year={2025}
+}
+```