model-replacement-runtime

interfaces/classification.py

@@ -1,7 +1,7 @@
 from gliner import GLiNER
 import gradio as gr
 
-model = GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0").to("cpu")
+model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5").to("cpu")
 
 PROMPT_TEMPLATE = """Classify the given text having the following classes: {}"""
 classification_examples = [

interfaces/landing.py

@@ -21,7 +21,7 @@ with gr.Blocks() as landing_interface:
         gr.Code(
             '''
 from gliner import GLiNER
-model = GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0")
+model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5")
 text = "Your text here"
 labels = ["person", "award", "date", "competitions", "teams"]
 entities = model.predict_entities(text, labels)

interfaces/ner.py

@@ -2,7 +2,7 @@ from typing import Dict, Union
 from gliner import GLiNER
 import gradio as gr
 
-model = GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0").to("cpu")
+model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5").to("cpu")
 
 text1 = """
 "I recently purchased the Sony WH-1000XM4 Wireless Noise-Canceling Headphones from Amazon and I must say, I'm thoroughly impressed. The package arrived in New York within 2 days, thanks to Amazon Prime's expedited shipping.

interfaces/open_ie.py

@@ -2,7 +2,7 @@ from typing import Dict, Union
 from gliner import GLiNER
 import gradio as gr
 
-model = GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0").to("cpu")
+model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5").to("cpu")
 
 text1 = """
 "I recently purchased the Sony WH-1000XM4 Wireless Noise-Canceling Headphones from Amazon and I must say, I'm thoroughly impressed. The package arrived in New York within 2 days, thanks to Amazon Prime's expedited shipping.

interfaces/qa.py

@@ -2,7 +2,7 @@ from typing import Dict, Union
 from gliner import GLiNER
 import gradio as gr
 
-model = GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0").to("cpu")
+model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5").to("cpu")
 
 text2 = """
 Apple Inc. is an American multinational technology company headquartered in Cupertino, California. Apple is the world's largest technology company by revenue, with US$394.3 billion in 2022 revenue. As of March 2023, Apple is the world's biggest company by market capitalization. As of June 2022, Apple is the fourth-largest personal computer vendor by unit sales and the second-largest mobile phone manufacturer in the world. It is considered one of the Big Five American information technology companies, alongside Alphabet (parent company of Google), Amazon, Meta Platforms, and Microsoft.

interfaces/relation_e.py

@@ -21,7 +21,7 @@ Dr. Paul Hammond, a renowned neurologist at Johns Hopkins University, has recent
 
 predictor = GLiNERPredictor( # Predictor manages the model that will be used by tasks
     GLiNERPredictorConfig(
-        model_name = "knowledgator/gliner-multitask-v1.0", # Model to use
+        model_name = "knowledgator/gliner-multitask-large-v0.5", # Model to use
         device = "cpu", # Device to use
     )
 )

interfaces/summarization.py

@@ -2,7 +2,7 @@ from typing import Dict, Union
 from gliner import GLiNER
 import gradio as gr
 
-model = GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0").to('cpu')
+model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5").to('cpu')
 
 text1 = """
 "I recently purchased the Sony WH-1000XM4 Wireless Noise-Canceling Headphones from Amazon and I must say, I'm thoroughly impressed. The package arrived in New York within 2 days, thanks to Amazon Prime's expedited shipping.

interfaces/universal.py

@@ -2,7 +2,7 @@ from typing import Dict, Union
 from gliner import GLiNER
 import gradio as gr
 
-model = GLiNER.from_pretrained("knowledgator/gliner-multitask-v1.0").to('cpu')
+model = GLiNER.from_pretrained("knowledgator/gliner-multitask-large-v0.5").to('cpu')
 
 text1 = """
 "I recently purchased the Sony WH-1000XM4 Wireless Noise-Canceling Headphones from Amazon and I must say, I'm thoroughly impressed. The package arrived in New York within 2 days, thanks to Amazon Prime's expedited shipping.

materials/introduction.html

@@ -56,7 +56,7 @@
         <li><b>Open Information Extraction:</b> Extracts pieces of text given an open prompt from a user, for example, product description extraction.</li>
     </ol>
     <h3>What is <a href="https://github.com/urchade/GLiNER">GLiNER</a> HandyLab?</h3>
-    <p>GLiNER HandyLab serves as a foundational showcase of our technological capabilities within the universal information extraction. It enployes the model <a href="https://huggingface.co/knowledgator/gliner-multitask-v1.0">"knowledgator/gliner-multitask-v1.0"</a>. GLiNER-Multitask is a model designed to extract various pieces of information from plain text based on a user-provided custom prompt. This versatile model leverages a bidirectional transformer encoder, similar to BERT, which ensures both high generalization and compute efficiency despite its compact size.<p>
+    <p>GLiNER HandyLab serves as a foundational showcase of our technological capabilities within the universal information extraction. It enployes the model <a href="https://huggingface.co/knowledgator/gliner-multitask-large-v0.5">"knowledgator/gliner-multitask-large-v0.5"</a>. GLiNER-Multitask is a model designed to extract various pieces of information from plain text based on a user-provided custom prompt. This versatile model leverages a bidirectional transformer encoder, similar to BERT, which ensures both high generalization and compute efficiency despite its compact size.<p>
     <h3>Remember, information extraction is not just about data; it's about insights. Let's uncover those insights together!💫</h3>
     <!-- Links Section -->
     <div class="links-container">