Instructions to use launch/ThinkPRM-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use launch/ThinkPRM-7B with Transformers:

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

pipe = pipeline("text-generation", model="launch/ThinkPRM-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("launch/ThinkPRM-7B")
model = AutoModelForCausalLM.from_pretrained("launch/ThinkPRM-7B")
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 launch/ThinkPRM-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "launch/ThinkPRM-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "launch/ThinkPRM-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/launch/ThinkPRM-7B

SGLang

How to use launch/ThinkPRM-7B 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 "launch/ThinkPRM-7B" \
    --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": "launch/ThinkPRM-7B",
		"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 "launch/ThinkPRM-7B" \
        --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": "launch/ThinkPRM-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use launch/ThinkPRM-7B with Docker Model Runner:
```
docker model run hf.co/launch/ThinkPRM-7B
```

Add project page link to model card

by nielsr HF Staff - opened Sep 26, 2025

base: refs/heads/main

←

from: refs/pr/1

Discussion Files changed

-3

Files changed (1) hide show

README.md +5 -3

README.md CHANGED Viewed

@@ -1,5 +1,7 @@
 ---
 library_name: transformers
 tags:
 - reward-model
 - prm
@@ -9,8 +11,6 @@ tags:
 - verification
 - math reasoning
 - code verification
-license: apache-2.0
-pipeline_tag: text-generation
 ---
 # Model Card for ThinkPRM-7B
@@ -34,6 +34,7 @@ The model uses a standard language modeling objective, making it interpretable a
 - **Repository:** [Github](https://github.com/mukhal/thinkprm)
 - **Paper:** [Process Reward Models that Think (arXiv:2504.16828)](https://arxiv.org/abs/2504.16828)
 ### Direct Use
@@ -126,4 +127,5 @@ Critique: This step is incorrect. Dividing both sides of the equation 2x = 4 by
 Step 2 is \boxed{incorrect}
 </think>
 Is the solution correct? No
-"""

 ---
 library_name: transformers
+license: apache-2.0
+pipeline_tag: text-generation
 tags:
 - reward-model
 - prm
 - verification
 - math reasoning
 - code verification
 ---
 # Model Card for ThinkPRM-7B
 - **Repository:** [Github](https://github.com/mukhal/thinkprm)
 - **Paper:** [Process Reward Models that Think (arXiv:2504.16828)](https://arxiv.org/abs/2504.16828)
+- **Project Page:** [ThinkPRM Webpage](https://mukhal.github.io/projects/thinkprm/)
 ### Direct Use
 Step 2 is \boxed{incorrect}
 </think>
 Is the solution correct? No
+"""
+```