67 lines
2.1 KiB
Markdown
67 lines
2.1 KiB
Markdown
|
---
|
||
|
|
base_model: anujjamwal/OpenMath-Nemotron-1.5B-PruneAware
|
||
|
|
library_name: transformers
|
||
|
|
model_name: OpenMath-Nemotron-1.5B-PruneAware
|
||
|
|
tags:
|
||
|
|
- generated_from_trainer
|
||
|
|
- sft
|
||
|
|
- trl
|
||
|
|
- custom_generate
|
||
|
|
licence: license
|
||
|
|
datasets:
|
||
|
|
- anujjamwal/OpenMathReasoning-Sampled-Hierarchical-Cot
|
||
|
|
---
|
||
|
|
|
||
|
|
# Model Card for OpenMath-Nemotron-1.5B-PruneAware
|
||
|
|
|
||
|
|
This model implements [Cognitive Compression](https://github.com/anujjamwal/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](https://huggingface.co/anujjamwal/OpenMath-Nemotron-1.5B-PruneAware).
|
||
|
|
It has been trained using [TRL](https://github.com/huggingface/trl).
|
||
|
|
|
||
|
|
## Quick start
|
||
|
|
|
||
|
|
```python
|
||
|
|
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:
|
||
|
|
|
||
|
|
```bibtex
|
||
|
|
@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}
|
||
|
|
}
|
||
|
|
```
|