qgyd2021 commited on
Commit
d7efd4b
·
1 Parent(s): 7c047d7

Create README.md

Browse files

## Reward Model GPT2

fine-tuned [GPT2](https://huggingface.co/gpt2) to a reward model.

The model is designed to generate human-like responses to questions in [Stack Exchange](https://huggingface.co/datasets/lvwerra/stack-exchange-paired) domains of programming, mathematics, physics, and more.

For more info check out the blog post and github [example](https://github.com/huggingface/trl/tree/main/examples/research_projects/stack_llama_2/scripts).

Files changed (1) hide show
  1. README.md +11 -0
README.md ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ datasets:
4
+ - lvwerra/stack-exchange-paired
5
+ language:
6
+ - en
7
+ library_name: adapter-transformers
8
+ pipeline_tag: text-generation
9
+ tags:
10
+ - reward_model
11
+ ---