Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

[Enhancement] Refactor code to parameterize model selection #8

Merged
merged 1 commit into from
Nov 4, 2023
Merged

[Enhancement] Refactor code to parameterize model selection #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 16 additions & 2 deletions TigerRag/tigerrag/demo/movie_recs/demo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,6 +6,21 @@
import faiss
import openai
import os
from transformers import BertTokenizer, BertModel, RobertaTokenizer, RobertaModel, XLNetTokenizer, XLNetModel

def initialize_model(model_name):
if model_name == "bert":
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained('bert-base-uncased')
elif model_name == "roberta":
tokenizer = RobertaTokenizer.from_pretrained('roberta-base')
model = RobertaModel.from_pretrained('roberta-base')
elif model_name == "xlnet":
tokenizer = XLNetTokenizer.from_pretrained('xlnet-base-cased')
model = XLNetModel.from_pretrained('xlnet-base-cased')
else:
raise ValueError("Unsupported model name!")
return tokenizer, model

# openai.api_key = ""
# openai_api_key = os.environ.get('OPENAI_API_KEY')
Expand All @@ -18,8 +33,7 @@
queries_df = pd.read_csv('queries.csv')

# Initialize BERT tokenizer and model
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')
model = BertModel.from_pretrained('bert-base-uncased')
tokenizer, model = initialize_model("bert")

def get_embedding(text):
"""Returns the BERT embedding for a given text."""
Expand Down