# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForQuestionAnswering
tokenizer = AutoTokenizer.from_pretrained("OtterDev/otterchat2")
model = AutoModelForQuestionAnswering.from_pretrained("OtterDev/otterchat2", device_map="auto")Quick Links
OtterChat 2
OtterChat 2 is a brand-new version of OtterChat with new features!
Model Details
- Multilingual
- uses roberta now
Model Description
- Developed by: OtterDev
- Model type: Question Answering[Extractive]
- License: [More Information Needed]
- Finetuned from model: roberta-base-squad2
Model Sources
Uses
This model can be used to extract data from text, such as an essay.
Direct Use
[More Information Needed]
Out-of-Scope Use
[More Information Needed]
Bias, Risks, and Limitations
The main limitation of this model is you NEED to have data in order for it to work. More will be posted when more limitations are found. Another limitation is it is quite slow when translating languages.
Recommendations
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
How to Get Started with the Model
Select "Deploy" and select Interference API to get started.
- Downloads last month
- 16
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="OtterDev/otterchat2")