Instructions to use launch/ThinkPRM-1.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use launch/ThinkPRM-1.5B with Transformers:

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

pipe = pipeline("text-generation", model="launch/ThinkPRM-1.5B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("launch/ThinkPRM-1.5B")
model = AutoModelForCausalLM.from_pretrained("launch/ThinkPRM-1.5B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use launch/ThinkPRM-1.5B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "launch/ThinkPRM-1.5B"
# 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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/launch/ThinkPRM-1.5B

SGLang

How to use launch/ThinkPRM-1.5B 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-1.5B" \
    --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-1.5B",
		"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-1.5B" \
        --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-1.5B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use launch/ThinkPRM-1.5B with Docker Model Runner:
```
docker model run hf.co/launch/ThinkPRM-1.5B
```

mkhalifa commited on Apr 25, 2025

Commit

cbdb08d

verified ·

1 Parent(s): 593f8de

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -11,9 +11,9 @@ tags:
 - code verification
 ---
-# Model Card for ThinkPRM-14B
-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:
@@ -22,11 +22,11 @@ Here's an example of the model output:
 ### Model Description
-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.
-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.
-- **Finetuned from model [optional]:** [R1-Distill-Qwen-14B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-14B)
 ### Model Sources [optional]
@@ -36,7 +36,7 @@ The model uses a standard language modeling objective, making it interpretable a
 ### Direct Use
-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.
@@ -54,7 +54,7 @@ The model has been evaluated on mathematical reasoning (MATH, AIME), scientific
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from vllm import LLM, SamplingParams
-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)

 - code verification
 ---
+# Model Card for ThinkPRM-1.5B
+ThinkPRM-1.5B is a generative Process Reward Model (PRM) based on the R1-Distill-Qwen-1.5B 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 Description
+ThinkPRM-1.5B 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.
+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-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]
 ### Direct Use
+ThinkPRM-1.5B 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.
 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)