Hugging Face's logo

DukeNLP
/
Prob-Gen-8B

Text Generation
Transformers
Safetensors
llama
text-generation-inference
Model card Files
xet
 Community
DukeNLP commited on
Commit
d4e8d52
·
verified ·
1 Parent(s): 3c21d23

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -2
README.md CHANGED
@@ -5,8 +5,7 @@ tags: []
5
 
6
  # Model Card for Model ID
7
 
8
- This model is a fine-tuned based on [Llama-3-8B from Meta](https://huggingface.co/meta-llama/Meta-Llama-3-8B) for 3,644 GPT-4 generated grade school math word problems. The model generates math word problems with multiple choices under given contexts.
9
-
10
  <!--
11
  ## Model Details
12
 
 
5
 
6
  # Model Card for Model ID
7
 
8
+ This model has been fine-tuned using 4-bit QLORA, based on [Llama-3-8B from Meta](https://huggingface.co/meta-llama/Meta-Llama-3-8B), and utilizes 3,644 GPT-4-generated grade school math word problems. It generates math word problems with multiple choices within specified contexts.
 
9
  <!--
10
  ## Model Details
11