mt5-yakut

18
2
2 languages
license:apache-2.0
by
lab-ii
Language Model
OTHER
New
18 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

Model Prefixes `"translate Russian to Sakha: "` - Ru-sah `"translate Sakha to Russian: "` - sah-Ru

Training Data Analysis

🔵 Good (6.0/10)

Researched training datasets used by mt5-yakut with quality assessment

Specialized For

general
multilingual

Training Datasets (1)

c4
🔵 6/10
general
multilingual
Key Strengths
  • •Scale and Accessibility: 750GB of publicly available, filtered text
  • •Systematic Filtering: Documented heuristics enable reproducibility
  • •Language Diversity: Despite English-only, captures diverse writing styles
Considerations
  • •English-Only: Limits multilingual applications
  • •Filtering Limitations: Offensive content and low-quality text remain despite filtering

Explore our comprehensive training dataset analysis

View All Datasets

Code Examples

Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']
Model Prefixespythontransformers
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer

model = AutoModelForSeq2SeqLM.from_pretrained("lab-ii/mt5-yakut")
tokenizer = AutoTokenizer.from_pretrained("lab-ii/mt5-yakut")

def predict(text, prefix, a=32, b=3, max_input_length=1024, num_beams=3, **kwargs):
    inputs = tokenizer(prefix + text, return_tensors='pt', padding=True, truncation=True, max_length=max_input_length)
    result = model.generate(
        **inputs.to(model.device),
        max_new_tokens=int(a + b * inputs.input_ids.shape[1]),
        num_beams=num_beams,
        **kwargs
    )
    return tokenizer.batch_decode(result, skip_special_tokens=True)

sentence: str = "Фотограф опубликовал снимки с прошедшего феста."

translation = predict(sentence, prefix="translate Russian to Sakha: ")

print(translation)

# ['Бэрэограф ааспыт фесттан хаартыскалары ыытан көрдөрбүт.']

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.

Try Free API

Replicate

One-click model deployment

Easiest Setup

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

Deploy Now

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