Chatrag-Deberta
is a small lightweight LLM to predict whether a question should retrieve additional information with RAG or not.
Chatrag-Deberta is based on Deberta-v3-large, a 304M encoder-decoder. Its initial version was fine-tuned on 20,000 examples of questions annotated by Mistral 7B.
Use
A typical example of inference with Chatrag-Deberta is provided in the
Google Colab demo
or with inference_chatrag.py
For every submitted text, Chatrag-Deberta will output a range of probabilities to require RAG or not.
This makes it possible to adjust a threshold of activation depending on whether more or less RAG is desirable in the system.
Query
Prob
Result
Comment puis-je renouveler un passeport ?
0.988455
RAG
Combien font deux et deux ?
0.041475
No-RAG
Écris un début de lettre de recommandation pour la Dinum
0.103086
No-RAG
Runs of AgentPublic chatrag-deberta on huggingface.co
6
Total runs
1
24-hour runs
1
3-day runs
1
7-day runs
4
30-day runs
More Information About chatrag-deberta huggingface.co Model
chatrag-deberta huggingface.co
chatrag-deberta huggingface.co is an AI model on huggingface.co that provides chatrag-deberta's model effect (), which can be used instantly with this AgentPublic chatrag-deberta model. huggingface.co supports a free trial of the chatrag-deberta model, and also provides paid use of the chatrag-deberta. Support call chatrag-deberta model through api, including Node.js, Python, http.
chatrag-deberta huggingface.co is an online trial and call api platform, which integrates chatrag-deberta's modeling effects, including api services, and provides a free online trial of chatrag-deberta, you can try chatrag-deberta online for free by clicking the link below.
AgentPublic chatrag-deberta online free url in huggingface.co:
chatrag-deberta is an open source model from GitHub that offers a free installation service, and any user can find chatrag-deberta on GitHub to install. At the same time, huggingface.co provides the effect of chatrag-deberta install, users can directly use chatrag-deberta installed effect in huggingface.co for debugging and trial. It also supports api for free installation.