microsoft/DialogRPT-updown ↗
- source model id
- HuggingFace/microsoft-dialogrpt-updown@5
- hosting
- foundry-managed-compute
- platforms
- Microsoft Foundry
- architecture
- input_modalities
- output_modalities
- capabilities
# Demo Please try this [➤➤➤ Colab Notebook Demo (click me!)](https://colab.research.google.com/drive/1cAtfkbhqsRsT59y3imjR1APw3MHDMkuV?usp=sharing) | Context | Response | `updown` score | | :------ |…
azureFoundry/HuggingFace/microsoft-dialogrpt-updown@6
Please try this ➤➤➤ Colab Notebook Demo (click me!)
| Context | Response | updown score |
|---|---|---|
| I love NLP! | Here’s a free textbook (URL) in case anyone needs it. | 0.613 |
| I love NLP! | Me too! | 0.111 |
The updown score predicts how likely the response is getting upvoted.
How likely a dialog response is upvoted 👍 and/or gets replied 💬?
This is what DialogRPT is learned to predict. It is a set of dialog response ranking models proposed by Microsoft Research NLP Group trained on 100 + millions of human feedback data. It can be used to improve existing dialog generation model (e.g., DialoGPT) by re-ranking the generated response candidates.
Quick Links:
We considered the following tasks and provided corresponding pretrained models. This page is for the updown task, and other model cards can be found in table below.
| Task | Description | Pretrained model |
|---|---|---|
| Human feedback | given a context and its two human responses, predict... | |
updown | ... which gets more upvotes? | this model |
width | ... which gets more direct replies? | model card |
depth | ... which gets longer follow-up thread? | model card |
| Human-like (human vs fake) | given a context and one human response, distinguish it with... | |
human_vs_rand | ... a random human response | model card |
human_vs_machine | ... a machine generated response | model card |
Please create an issue on our repo
@inproceedings{gao2020dialogrpt,
title={Dialogue Response RankingTraining with Large-Scale Human Feedback Data},
author={Xiang Gao and Yizhe Zhang and Michel Galley and Chris Brockett and Bill Dolan},
year={2020},
booktitle={EMNLP}
}
microsoft/DialogRPT-updown powered by Text Generation Inference (TGI)
You can use cURL or any REST Client to send a request to the AzureML endpoint with your AzureML token.
curl <AZUREML_ENDPOINT_URL> \
-X POST \
-d '{"inputs":"What is Deep Learning?"}' \
-H "Authorization: Bearer <AZUREML_TOKEN>" \
-H "Content-Type: application/json"
{
"inputs": "What is Deep Learning?",
"parameters": {
"do_sample": true,
"top_p": 0.95,
"temperature": 0.2,
"top_k": 50,
"max_new_tokens": 256,
"repetition_penalty": 1.03,
"stop": ["\nUser:", "<|endoftext|>", "</s>"]
}
}
Additionally, Text Generation Inference (TGI) offers an OpenAI Chat Completion API compatible layer under the endpoint /v1/chat/completions,
check the full specification in the OpenAI Chat Completion Create Documentation.
1–2 / 2
1–5 / 5
Hugging Face · microsoft/DialogRPT-updown ↗
Microsoft Foundry · Model page ↗
Microsoft Foundry · Model page ↗
1–1 / 1
These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.