EleutherAI
/
gpt-neo-2.7B
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Stella Biderman 2021-04-12 17:18:31 +00:00 committed by huggingface-web
parent 5640038a91
commit 3e1c92ca77
1 changed files with 19 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

30
README.md
View File

@ -48,25 +48,33 @@ GPT-Neo was trained as an autoregressive language model. This means that its cor
GPT-Neo was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending on your usecase GPT-Neo may produce socially unacceptable text. See Sections 5 and 6 of the Pile paper for a more detailed analysis of the biases in the Pile. GPT-Neo was trained on the Pile, a dataset known to contain profanity, lewd, and otherwise abrasive language. Depending on your usecase GPT-Neo may produce socially unacceptable text. See Sections 5 and 6 of the Pile paper for a more detailed analysis of the biases in the Pile.
As with all language models, it is hard to predict in advance how GPT-Neo will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results. As with all language models, it is hard to predict in advance how GPT-Neo will respond to particular prompts and offensive content may occur without warning. We recommend having a human curate or filter the outputs before releasing them, both to censor undesirable content and to improve the quality of the results.
## Eval results ## Eval results
### Language Modeling Baselines All evaluations were done using our [evaluation harness](https://github.com/EleutherAI/lm-evaluation-harness). Some results for GPT-2 and GPT-3 are inconsistent with the values reported in the respective papers. We are currently looking into why, and would greatly appreciate feedback and further testing of our eval harness. If you would like to contribute evaluations you have done, please reach out on our [Discord](https://discord.gg/vtRgjbM).
EleutherAI is currently in the process of carrying out further evaluations of GPT-Neo. The following table should be considered a work-in-progress. If you would like to contribute evaluations you have done, please reach out on our Discord. ### Linguistic Reasoning
| Model and Size | Pile BPB | Pile PPL | Wikitext PPL. | | Model and Size | Pile BPB | Pile PPL | Wikitext PPL | Lambada PPL | Lambada Acc | Winogrande | Hellaswag |
| ---------------- | ------------- | ------------- | -------------- | | ---------------- | ---------- | ---------- | ------------- | ----------- | ----------- | ---------- | ----------- |
| GPT-Neo 1.3B | 0.7527 | 6.159 | 13.10 | | GPT-Neo 1.3B | 0.7527 | 6.159 | 13.10 | 7.498 | 57.23% | 55.01% | 38.66% |
| GPT-3 1.3B | ------ | ----- | ----- | | GPT-2 1.5B | 1.0468 | ----- | 17.48 | 10.634 | 51.21% | 59.40% | 40.03% |
| GPT-2 1.5B | 1.0468 | ----- | 17.48 | | **GPT-Neo 2.7B** | **0.7165** | **5.646** | **11.39** | **5.626** | **62.22%** | **56.50%** | **42.73%** |
| **GPT-Neo 2.7B** | **0.7165** | **5.646** | **11.39** | | GPT-3 Ada | 0.9631 | ----- | ----- | 9.954 | 51.60% | 52.90% | 35.93% |
| GPT-3 2.7B | 0.9631 | ----- | ----- |
| GPT-3 175B | 0.7177 | ----- | ----- |
All GPT-2 and GPT-3 scores are from their respective papers, except for the Pile test results which are from the Pile paper. ### Physical and Scientific Reasoning
| Model and Size | MathQA | PubMedQA | Piqa |
| ---------------- | ---------- | ---------- | ----------- |
| GPT-Neo 1.3B | 24.05% | 54.40% | 71.11% |
| GPT-2 1.5B | 23.64% | 58.33% | 70.78% |
| **GPT-Neo 2.7B** | **24.72%** | **57.54%** | **72.14%** |
| GPT-3 Ada | 24.29% | 52.80% | 68.88% |
### Down-Stream Applications ### Down-Stream Applications
TBD
### BibTeX entry and citation info ### BibTeX entry and citation info
```bibtex ```bibtex