Instructions to use prithivMLmods/Deepthink-1.5B-Open-PRM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prithivMLmods/Deepthink-1.5B-Open-PRM with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prithivMLmods/Deepthink-1.5B-Open-PRM")
model = AutoModelForCausalLM.from_pretrained("prithivMLmods/Deepthink-1.5B-Open-PRM")
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 prithivMLmods/Deepthink-1.5B-Open-PRM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prithivMLmods/Deepthink-1.5B-Open-PRM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prithivMLmods/Deepthink-1.5B-Open-PRM",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prithivMLmods/Deepthink-1.5B-Open-PRM

SGLang

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

Docker Model Runner
How to use prithivMLmods/Deepthink-1.5B-Open-PRM with Docker Model Runner:
```
docker model run hf.co/prithivMLmods/Deepthink-1.5B-Open-PRM
```

prithivMLmods commited on Apr 24, 2025

Commit

012150f

verified ·

1 Parent(s): 4557992

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -17,7 +17,7 @@ pipeline_tag: text-generation
 # **Deepthink-1.5B-Open-PRM**
-> **Deepthink-1.5B-Open-PRM** is a **process-supervised reasoning model** fine-tuned from **Qwen2.5 0.5B** using **Process Reward Models (PRM)**. It excels at **step-by-step mathematical problem solving** in both **English** and **Simplified Chinese**, offering interpretable, logically structured responses for use in **education**, **STEM tutoring**, and **lightweight math agents**.
 ## **Key Features**
@@ -25,7 +25,7 @@ pipeline_tag: text-generation
    Fine-tuned with PRMs to reward high-quality intermediate reasoning steps — fostering step-by-step interpretability, accuracy, and educational transparency.
 2. **Compact Foundation (Qwen2.5 0.5B)**
-   Built upon the highly efficient Qwen2.5 0.5B architecture and scaled up through distillation and reward-based alignment to 1.5B parameters, balancing reasoning quality and deployment efficiency.
 3. **Bilingual Math Capability**
    Fluent in solving and explaining math problems in both **English** and **Simplified Chinese**, making it ideal for multilingual classrooms and tutoring platforms.

 # **Deepthink-1.5B-Open-PRM**
+> **Deepthink-1.5B-Open-PRM** is a **process-supervised reasoning model** fine-tuned from **Qwen2.5 1.5B** using **Process Reward Models (PRM)**. It excels at **step-by-step mathematical problem solving** in both **English** and **Simplified Chinese**, offering interpretable, logically structured responses for use in **education**, **STEM tutoring**, and **lightweight math agents**.
 ## **Key Features**
    Fine-tuned with PRMs to reward high-quality intermediate reasoning steps — fostering step-by-step interpretability, accuracy, and educational transparency.
 2. **Compact Foundation (Qwen2.5 0.5B)**
+   Built upon the highly efficient Qwen2.5 1.5B architecture and scaled up through distillation and reward-based alignment to 1.5B parameters, balancing reasoning quality and deployment efficiency.
 3. **Bilingual Math Capability**
    Fluent in solving and explaining math problems in both **English** and **Simplified Chinese**, making it ideal for multilingual classrooms and tutoring platforms.