Downloads · 30 days
18
2% of all-time downloads
Saisam/gpt-neo-math-small
gpt-neo-math-small is a text generation model from Saisam. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
In the project, we used an HuggingFace GPT-NEO small model and fine-tuned the tactic dataset. The Input should be of the form
Downloads · 30 days
18
2% of all-time downloads
All-time downloads
1.1K
Public
Repo size
1.1 GB
Likes
0
Public
Click a slice to open those files.
.bin551 MB · 100%
From the Hugging Face model README
In the project, we used an HuggingFace GPT-NEO small model and fine-tuned the tactic dataset. The Input should be of the form
<GOAL> Goal <PROOFSTEP>
The model can easily be accessed using the following code.
from transformers import GPT2Tokenizer, GPTNeoForCausalLM
import torch
tokenizer = GPT2Tokenizer.from_pretrained("Saisam/gpt-neo-math-small")
model = GPTNeoForCausalLM.from_pretrained("Saisam/gpt-neo-math-small")
More Information can be found at https://github.com/saisurbehera/mathProof.
The current model beats the GPT-F for minif2f benchmark
Worked along with Xihao Xhang and Moya Zhu