Downloads · 30 days
16
44% of all-time downloads
src_ctx_and_term_nllb_600M_onnx
voxreality/src_ctx_and_term_nllb_600M_onnx
src_ctx_and_term_nllb_600M_onnx is a machine learning model from voxreality. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
ONNX format of voxreality/srcctxandtermnllb600M model
All-time downloads
36
Public
Repo size
5.3 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx5.3 GB · 100%
At a glance
- License
- apache-2.0
- Model type
- m2m_100
- Access
- Public
- Created
- Apr 23, 2025
- Updated
- Apr 29, 2025
- SHA
- 4d976194
Model card
From the Hugging Face model README
ONNX format of voxreality/src_ctx_and_term_nllb_600M model
Model inference example:
from optimum.onnxruntime import ORTModelForSeq2SeqLM
from transformers import AutoTokenizer,pipeline
model_path = 'voxreality/src_ctx_and_term_nllb_600M_onnx'
model = ORTModelForSeq2SeqLM.from_pretrained(model_path)
tokenizer = AutoTokenizer.from_pretrained(model_path)
onnx_translation = pipeline("translation_en_to_de", model=model, tokenizer=tokenizer)
max_length = 100
src_lang = 'eng_Latn'
tgt_lang = 'deu_Latn'
context_text = 'This is an optional context sentence.'
target_term = 'text'
sentence_text = 'Text to be translated.'
input_text = f'{context_text} {tokenizer.sep_token} {sentence_text} {tokenizer.sep_token} {target_term}'
forced_bos_token_id = tokenizer.lang_code_to_id[tgt_lang]
output = model.generate(
**tokenizer(input_text, return_tensors='pt'),
forced_bos_token_id=forced_bos_token_id,
max_length=max_length
)
output_text = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
print(output_text)
- Type
- m2m_100
- License
- apache-2.0
- Created
- Apr 23, 2025
- Updated
- Apr 29, 2025