Geolm Base Toponym Recognition

135

8

1 language

license:cc-by-nc-2.0

by

zekun-li

Other

OTHER

New

135 downloads

Early-stage

Try on Hugging Face Add to Compare

Edge AI:

Mobile

Laptop

Server

Unknown

Mobile

Laptop

Server

Quick Summary

A language model for detecting toponyms (i.

Code Examples

Model name from Hugging Face model hubpythontransformers

import torch
from transformers import AutoModelForTokenClassification, AutoTokenizer


# Model name from Hugging Face model hub
model_name = "zekun-li/geolm-base-toponym-recognition"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Example input sentence
input_sentence = "Minneapolis, officially the City of Minneapolis, is a city in the state of Minnesota and the county seat of Hennepin County."

# Tokenize input sentence
tokens = tokenizer.encode(input_sentence, return_tensors="pt")

# Pass tokens through the model
outputs = model(tokens) 

# Retrieve predicted labels for each token
predicted_labels = torch.argmax(outputs.logits, dim=2)

predicted_labels = predicted_labels.detach().cpu().numpy()

# Decode predicted labels
predicted_labels = [model.config.id2label[label] for label in predicted_labels[0]]

# Print predicted labels
print(predicted_labels)
# ['O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'O',
# 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'I-Topo', 'I-Topo', 'O', 'O', 'O']

Model name from Hugging Face model hubpythontransformers

import torch
from transformers import AutoModelForTokenClassification, AutoTokenizer


# Model name from Hugging Face model hub
model_name = "zekun-li/geolm-base-toponym-recognition"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Example input sentence
input_sentence = "Minneapolis, officially the City of Minneapolis, is a city in the state of Minnesota and the county seat of Hennepin County."

# Tokenize input sentence
tokens = tokenizer.encode(input_sentence, return_tensors="pt")

# Pass tokens through the model
outputs = model(tokens) 

# Retrieve predicted labels for each token
predicted_labels = torch.argmax(outputs.logits, dim=2)

predicted_labels = predicted_labels.detach().cpu().numpy()

# Decode predicted labels
predicted_labels = [model.config.id2label[label] for label in predicted_labels[0]]

# Print predicted labels
print(predicted_labels)
# ['O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'O',
# 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'I-Topo', 'I-Topo', 'O', 'O', 'O']

Model name from Hugging Face model hubpythontransformers

import torch
from transformers import AutoModelForTokenClassification, AutoTokenizer


# Model name from Hugging Face model hub
model_name = "zekun-li/geolm-base-toponym-recognition"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Example input sentence
input_sentence = "Minneapolis, officially the City of Minneapolis, is a city in the state of Minnesota and the county seat of Hennepin County."

# Tokenize input sentence
tokens = tokenizer.encode(input_sentence, return_tensors="pt")

# Pass tokens through the model
outputs = model(tokens) 

# Retrieve predicted labels for each token
predicted_labels = torch.argmax(outputs.logits, dim=2)

predicted_labels = predicted_labels.detach().cpu().numpy()

# Decode predicted labels
predicted_labels = [model.config.id2label[label] for label in predicted_labels[0]]

# Print predicted labels
print(predicted_labels)
# ['O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'O',
# 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'I-Topo', 'I-Topo', 'O', 'O', 'O']

Model name from Hugging Face model hubpythontransformers

import torch
from transformers import AutoModelForTokenClassification, AutoTokenizer


# Model name from Hugging Face model hub
model_name = "zekun-li/geolm-base-toponym-recognition"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Example input sentence
input_sentence = "Minneapolis, officially the City of Minneapolis, is a city in the state of Minnesota and the county seat of Hennepin County."

# Tokenize input sentence
tokens = tokenizer.encode(input_sentence, return_tensors="pt")

# Pass tokens through the model
outputs = model(tokens) 

# Retrieve predicted labels for each token
predicted_labels = torch.argmax(outputs.logits, dim=2)

predicted_labels = predicted_labels.detach().cpu().numpy()

# Decode predicted labels
predicted_labels = [model.config.id2label[label] for label in predicted_labels[0]]

# Print predicted labels
print(predicted_labels)
# ['O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'O',
# 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'I-Topo', 'I-Topo', 'O', 'O', 'O']

Model name from Hugging Face model hubpythontransformers

import torch
from transformers import AutoModelForTokenClassification, AutoTokenizer


# Model name from Hugging Face model hub
model_name = "zekun-li/geolm-base-toponym-recognition"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Example input sentence
input_sentence = "Minneapolis, officially the City of Minneapolis, is a city in the state of Minnesota and the county seat of Hennepin County."

# Tokenize input sentence
tokens = tokenizer.encode(input_sentence, return_tensors="pt")

# Pass tokens through the model
outputs = model(tokens) 

# Retrieve predicted labels for each token
predicted_labels = torch.argmax(outputs.logits, dim=2)

predicted_labels = predicted_labels.detach().cpu().numpy()

# Decode predicted labels
predicted_labels = [model.config.id2label[label] for label in predicted_labels[0]]

# Print predicted labels
print(predicted_labels)
# ['O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'O',
# 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'I-Topo', 'I-Topo', 'O', 'O', 'O']

Model name from Hugging Face model hubpythontransformers

import torch
from transformers import AutoModelForTokenClassification, AutoTokenizer


# Model name from Hugging Face model hub
model_name = "zekun-li/geolm-base-toponym-recognition"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Example input sentence
input_sentence = "Minneapolis, officially the City of Minneapolis, is a city in the state of Minnesota and the county seat of Hennepin County."

# Tokenize input sentence
tokens = tokenizer.encode(input_sentence, return_tensors="pt")

# Pass tokens through the model
outputs = model(tokens) 

# Retrieve predicted labels for each token
predicted_labels = torch.argmax(outputs.logits, dim=2)

predicted_labels = predicted_labels.detach().cpu().numpy()

# Decode predicted labels
predicted_labels = [model.config.id2label[label] for label in predicted_labels[0]]

# Print predicted labels
print(predicted_labels)
# ['O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'O',
# 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'I-Topo', 'I-Topo', 'O', 'O', 'O']

Model name from Hugging Face model hubpythontransformers

import torch
from transformers import AutoModelForTokenClassification, AutoTokenizer


# Model name from Hugging Face model hub
model_name = "zekun-li/geolm-base-toponym-recognition"

# Load tokenizer and model
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Example input sentence
input_sentence = "Minneapolis, officially the City of Minneapolis, is a city in the state of Minnesota and the county seat of Hennepin County."

# Tokenize input sentence
tokens = tokenizer.encode(input_sentence, return_tensors="pt")

# Pass tokens through the model
outputs = model(tokens) 

# Retrieve predicted labels for each token
predicted_labels = torch.argmax(outputs.logits, dim=2)

predicted_labels = predicted_labels.detach().cpu().numpy()

# Decode predicted labels
predicted_labels = [model.config.id2label[label] for label in predicted_labels[0]]

# Print predicted labels
print(predicted_labels)
# ['O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'O',
# 'O', 'O', 'B-Topo', 'O', 'O', 'O', 'O', 'O', 'B-Topo', 'I-Topo', 'I-Topo', 'O', 'O', 'O']

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.