Update README.md

README.md

@@ -1,199 +1,114 @@
 ---
 library_name: transformers
-tags: []
+tags:
+- reward-model
+- prm
+- generative reward model
+- process supervision
+- chain-of-thought
+- verification
+- math reasoning
+- code verification
 ---
 
-# Model Card for Model ID
+# Model Card for ThinkPRM-14B
 
-<!-- Provide a quick summary of what the model is/does. -->
+ThinkPRM-14B is a generative Process Reward Model (PRM) based on the R1-Distill-Qwen-14B architecture. It is fine-tuned to perform step-by-step verification of reasoning processes (like mathematical solutions) by generating an explicit verification chain-of-thought (CoT) that involves labeling every step. It is designed to be highly data-efficient, requiring significantly less supervision data than traditional discriminative PRMs while achieving strong performance.
 
+Here's an example of the model output: 
 
 
 ## Model Details
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+ThinkPRM-14B provides step-level verification scores by generating natural language critiques and correctness judgments for each step in a given solution prefix. It leverages 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.
 
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+The model uses a standard language modeling objective, making it interpretable and allowing it to scale process verification compute by generating longer or multiple verification CoTs. It demonstrated superior performance compared to LLM-as-a-judge and discriminative PRM baselines (based on the same R1-Distill-Qwen-14B model but trained on ~100x more labels) on benchmarks including ProcessBench, MATH-500, AIME '24, GPQA-Diamond, and LiveCodeBench.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Finetuned from model [optional]:** [R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)
 
 ### Model Sources [optional]
 
-<!-- Provide the basic links for the model. -->
+- **Repository:** [Github](https://github.com/mukhal/thinkprm)
+- **Paper:** [Process Reward Models that Think (arXiv:2504.16828)](https://arxiv.org/abs/2504.16828)
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
 ### Direct Use
 
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+ThinkPRM-14B is intended for verifying the correctness of step-by-step reasoning processes. Primary uses include:
+- **Scoring Solutions:** Assigning 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:** Producing detailed chain-of-thought verifications that explain *why* a particular step is correct or incorrect, aiding interpretability.
+- **Standalone Verification:** Evaluating the correctness of a given problem-solution pair.
 
-[More Information Needed]
+The model has been evaluated on mathematical reasoning (MATH, AIME), scientific QA (GPQA), and code generation (LiveCodeBench). See our paper for more details.
 
-## Bias, Risks, and Limitations
+## Limitations
 
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+- **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).
 
 ## How to Get Started with the Model
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from vllm import LLM, SamplingParams
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
+model_id = "launch/ThinkPRM-14B" # Replace with actual model ID on Hub
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+llm = LLM(model=model_id, max_model_len=16384)
 
-[More Information Needed]
+# 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 = 2"
 
-#### Software
+# Format the prompt -- this is the prompt used for the results in the paper.
+prompt = f"""You are given a math problem and a proposed step-by-step solution:
 
-[More Information Needed]
+[Math Problem]
 
-## Citation [optional]
+{problem}
 
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+[Solution]
 
-**BibTeX:**
+{prefix}
 
-[More Information Needed]
+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
+"""
 
-**APA:**
+prompt = tokenizer.apply_chat_template([
+    {'role': "user", "content": prompt}
+], tokenize=False, add_generation_prompt=True) # construct prompt 
 
-[More Information Needed]
+# Set sampling parameters
+sampling_params = SamplingParams(
+    temperature=0.0,
+    max_tokens=4096,
+    stop=None
+)
 
-## Glossary [optional]
+# Generate the verification
+outputs = llm.generate(prompt, sampling_params)
+verification_cot = outputs[0].outputs[0].text
 
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+print(verification_cot)
+# Alright, I've got this math problem to solve: 2x + 3 = 7. And there's a proposed solution in multiple steps that I need to review and critique.
+# ...
+# Yes, that checks out. So, the solution is correct.
 
-[More Information Needed]
+# Alternatively, I could think about it differently. Maybe I could first divide both sides by 2, but that would give me x + 1.5 = 3.5, and then subtract 1.5 from both sides to get x = 2. But that's more complicated than the given solution.
 
-## More Information [optional]
+# The given solution is straightforward and efficient.
 
-[More Information Needed]
+# So, in conclusion, both steps are correct, and the solution is accurate.
 
-## Model Card Authors [optional]
+# But according to the instructions, since both steps are correct, I don't need to go into more detail. I just need to state that each step is correct.
 
-[More Information Needed]
+# So, my output should be:
 
-## Model Card Contact
+# Step 1: The step is to subtract 3 from both sides, resulting in 2x = 4. This is a correct operation to isolate the term with x. The step is \boxed{correct}
+#
+## Step 2: The step is to divide both sides by 2, resulting in x = 2. This is the correct operation to solve for x. The step is \boxed{correct}
 
-[More Information Needed]
+# </think>
+# Is the solution correct? Yes