Thinkprm 1.5B

🚀 ThinkPRM-1.5B Model Card

ThinkPRM-1.5B is a generative Process Reward Model (PRM) based on the R1 - Distill - Qwen - 1.5B architecture. It can perform step - by - step verification of reasoning processes (such as mathematical solutions) by generating an explicit verification chain - of - thought (CoT) with every step labeled. This model is highly data - efficient, requiring significantly less supervision data than traditional discriminative PRMs while achieving strong performance.

Here's an example of the model output:

📚 Documentation

📋 Model Description

ThinkPRM-1.5B offers step - level verification scores by generating natural language critiques and correctness judgments for each step in a given solution prefix. It utilizes the underlying reasoning capabilities of the base Large Reasoning Model (LRM) and enhances them through fine - tuning on a small (1K examples) dataset of synthetically generated verification CoTs. These synthetic CoTs were produced by prompting QwQ - 32B - Preview and filtered against ground - truth step labels from the PRM800K dataset to ensure quality.

The model uses a standard language modeling objective, which makes it interpretable and allows it to scale process verification compute by generating longer or multiple verification CoTs. It outperformed LLM - as - a - judge and discriminative PRM baselines (based on the same R1 - Distill - Qwen - 1.5B model but trained on ~100x more labels) on benchmarks including ProcessBench, MATH - 500, AIME '24, GPQA - Diamond, and LiveCodeBench.

• Finetuned from model [optional]: [R1 - Distill - Qwen - 1.5B](https://huggingface.co/deepseek - ai/DeepSeek - R1 - Distill - Qwen - 1.5B)

🌐 Model Sources [optional]

• Repository: Github
• Paper: Process Reward Models that Think (arXiv:2504.16828)

💼 Direct Use

ThinkPRM-1.5B is designed for verifying the correctness of step - by - step reasoning processes. Its primary uses include:

• Scoring Solutions: Assign step - level or overall scores to candidate solutions for ranking in Best - of - N sampling or guiding tree search in reasoning tasks.
• Generating Verification Rationales/CoTs: Produce detailed chain - of - thought verifications that explain why a particular step is correct or incorrect, aiding interpretability.
• Standalone Verification: Evaluate the correctness of a given problem - solution pair.

The model has been evaluated on mathematical reasoning (MATH, AIME), scientific QA (GPQA), and code generation (LiveCodeBench). See our paper for more details.

⚠️ Limitations

• Overconfidence: Generative PRMs like ThinkPRM can sometimes produce scores clustered near 0 or 1, potentially not reflecting true uncertainty.
• Step Label Interference: The autoregressive nature might cause an early incorrect step judgment to negatively bias the evaluation of subsequent steps.
• Sensitivity to Formatting/Prompting: Performance might be sensitive to the exact format of the input solution and the prompt used for verification (though fine - tuning likely reduces this compared to LLM - as - a - judge).

🚀 Quick Start

from transformers import AutoModelForCausalLM, AutoTokenizer
from vllm import LLM, SamplingParams

model_id = "launch/ThinkPRM-1.5B" # Replace with actual model ID on Hub
tokenizer = AutoTokenizer.from_pretrained(model_id)
llm = LLM(model=model_id, max_model_len=16384)

# Example problem and solution
problem = "Solve for x: 2x + 3 = 7"
prefix = "Step 1: Subtract 3 from both sides: 2x = 4\nStep 2: Divide by 2: x = 1"

# Format the prompt
prompt = f"""You are given a math problem and a proposed step-by-step solution:

[Math Problem]

{problem}

[Solution]

{prefix}

Review and critique each step in the proposed solution to determine whether each step is correct. If the solution is incomplete, only verify the provided steps
"""

prompt = tokenizer.apply_chat_template([
    {'role': "user", "content": prompt}
], tokenize=False, add_generation_prompt=True) + "\nLet's verify step by step:"

# Set sampling parameters
sampling_params = SamplingParams(
    temperature=0.0,
    max_tokens=4096,
    stop=None
)

# Generate the verification
outputs = llm.generate(prompt, sampling_params)
verification_cot = outputs[0].outputs[0].text

print(verification_cot)
"""
Step 1: Subtract 3 from both sides: 2x = 4

Critique: Starting with the equation 2x + 3 = 7, subtracting 3 from both sides is a correct operation to isolate the term with the variable. So, 2x + 3 - 3 = 7 - 3, which simplifies
 to 2x = 4. This step seems correct.

Step 2: Divide by 2: x = 1

Critique: Now, to solve for x, we need to divide both sides of the equation by 2. So, 2x / 2 = 4 / 2, which simplifies to x = 2. Wait a minute, the solution says x = 1, but accordin
g to this calculation, it should be x = 2. This seems incorrect.

Therefore, the first step is correct, but the second step has an error.

**Final Output:**

Let's verify step by step:

Step 1: Subtract 3 from both sides: 2x = 4

Critique: This step is correct. Subtracting 3 from both sides of the equation 2x + 3 = 7 properly isolates the term with the variable, resulting in 2x = 4.

Step 1 is \boxed{correct}

Step 2: Divide by 2: x = 1

Critique: This step is incorrect. Dividing both sides of the equation 2x = 4 by 2 should yield x = 2, not x = 1.

Step 2 is \boxed{incorrect}
</think>
Is the solution correct? No
"""

📄 License

The license of this model is apache - 2.0.