Instructions to use R4kSo1997/opus-mt-ca-fr-onnx-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use R4kSo1997/opus-mt-ca-fr-onnx-int8 with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "translation" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("translation", model="R4kSo1997/opus-mt-ca-fr-onnx-int8")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("R4kSo1997/opus-mt-ca-fr-onnx-int8") model = AutoModelForSeq2SeqLM.from_pretrained("R4kSo1997/opus-mt-ca-fr-onnx-int8") - Notebooks
- Google Colab
- Kaggle
opus-mt-ca-fr ONNX int8 (movil offline)
Conversion movil-ready de Helsinki-NLP/opus-mt-ca-fr.
ONNX
- encoder_model_quantized.onnx
- decoder_model_quantized.onnx
- decoder_with_past_model_quantized.onnx (KV cache, decoding O(1) por token)
Quant: int8 dynamic ARM64 + per_channel.
Tokenizer
- tokenizer.json (Fast / Xenova / transformers.js)
- source.spm, target.spm, vocab.json (Marian raw)
Source: Helsinki-NLP/opus-mt-ca-fr
Repo: R4kSo1997/opus-mt-ca-fr-onnx-int8
- Downloads last month
- 19