Instructions to use anujjamwal/OpenMath-Nemotron-1.5B-PruneAware with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use anujjamwal/OpenMath-Nemotron-1.5B-PruneAware with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("anujjamwal/OpenMath-Nemotron-1.5B-PruneAware")
model = AutoModelForCausalLM.from_pretrained("anujjamwal/OpenMath-Nemotron-1.5B-PruneAware")
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 anujjamwal/OpenMath-Nemotron-1.5B-PruneAware with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/anujjamwal/OpenMath-Nemotron-1.5B-PruneAware

SGLang

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

Docker Model Runner
How to use anujjamwal/OpenMath-Nemotron-1.5B-PruneAware with Docker Model Runner:
```
docker model run hf.co/anujjamwal/OpenMath-Nemotron-1.5B-PruneAware
```

Model Card for OpenMath-Nemotron-1.5B-PruneAware

This model implements Cognitive Compression an approach to produce hierarchical structured chain of thought that can be actively pruned at inference time while maintaining the solution quality. Tradition Chain-of-Thought is append-onl; a token once generated remains in context for ever. Context compression introduces hierarchical reasoning where reasoning is broken into subproblems. Once the subproblem is solved, its full chain of thought can be discarded and replaced with the summary and solution dramatically reducing the context window pressure.

This model is a fine-tuned version of anujjamwal/OpenMath-Nemotron-1.5B-PruneAware. It has been trained using TRL.

Quick start

from transformers import pipeline

question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
generator = pipeline("text-generation", model="anujjamwal/OpenMath-Nemotron-1.5B-PruneAware", device="cuda")
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
print(output["generated_text"])

Training procedure

This model was trained with SFT.

Framework versions

TRL: 0.29.0
Transformers: 5.0.0
Pytorch: 2.10.0+cu128
Datasets: 4.0.0
Tokenizers: 0.22.2

Citations

Cite TRL as:

@misc{jamwal2026cognitivecompression,
  title   = {{Cognitive Compression: Hierarchical Chain of Thought for Efficient LLM Reasoning}},
  author  = {Jamwal, Anuj},
  url     = {huggingface.co/anujjamwal/OpenMath-Nemotron-1.5B-PruneAware},
  year    = {2026},
  note    = {CS224N Winter '26 Final Project: Stanford University}
}

Downloads last month: 10

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for anujjamwal/OpenMath-Nemotron-1.5B-PruneAware

Unable to build the model tree, the base model loops to the model itself. Learn more.

anujjamwal
/

OpenMath-Nemotron-1.5B-PruneAware