Downloads · 30 days
27
15% of all-time downloads
eagle0504/openai-gsm8k-codealpaca-20k-enhanced-deepseek-r1-distill-qwen-1.5b
openai-gsm8k-codealpaca-20k-enhanced-deepseek-r1-distill-qwen-1.5b is a question answering model from eagle0504. Use it when the input is a question plus a passage. It is set up for transformers. The card lists the license as mit.
This model is fine-tuned to answer questions based on the CodeAlpaca-20k dataset enhanced with reasoning provided from Deepseek R1.
Downloads · 30 days
27
15% of all-time downloads
All-time downloads
176
Public
Parameters
1.8B
3.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors3.6 GB · 100%
From the Hugging Face model README
This model is fine-tuned to answer questions based on the CodeAlpaca-20k dataset enhanced with reasoning provided from Deepseek R1.
Invoke notebook shared here, a publicly available Colab notebook for tests.
This is a transformer-based question-answering model fine-tuned from eagle0504/finetuned-deepseek-r1-distill-qwen-1.5b-by-openai-gsm8k-enhanced-v2. It was trained on a dataset derived from the OpenAI GSM8K benchmark, enhanced with chain-of-thought reasoning to encourage intermediate logical steps. The dataset pairs math word problems with structured answers, using <think>...</think> and <answer>...</answer> tags.
runpod/pytorch:2.1.0-py3.10-cuda11.8.0-devel-ubuntu22.04<think>...</think><answer>...</answer> structure.To generate accurate completions, prompt the model in the following structure:
<question>Question: If Sally has 3 apples and buys 2 more, how many does she have in total?</question>
Be aware that this token </question> will prompt the answer to start with <think> which is trained into the model based on training data.
The model will continue reasoning within <think>...</think> and provide a final answer inside <answer>...</answer>.
This model is intended for educational and research purposes in:
If you use this model, please cite:
@misc{yin2024gsm8k,
author = {Yiqiao Yin},
title = {TBD},
year = 2025,
note = {TBD}
}
Author: Yiqiao Yin Connect with me on LinkedIn