Instructions to use jbochi/madlad400-3b-mt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jbochi/madlad400-3b-mt 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="jbochi/madlad400-3b-mt")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("jbochi/madlad400-3b-mt") model = AutoModelForSeq2SeqLM.from_pretrained("jbochi/madlad400-3b-mt") - Notebooks
- Google Colab
- Kaggle
Translation not working outputing garbage tokens
👍 1
6
#21 opened about 2 months ago
by
athaze
Error: POST predict: Post "http://127.0.0.1:44114/completion": EOF
#20 opened over 1 year ago
by
zerozj
Fine-Tuning Request
#19 opened almost 2 years ago
by
nikhiljais
Candle cannot inference madlad for gguf
1
#18 opened almost 2 years ago
by
thanasismem
Running out of memory with 12GB VRAM
1
#17 opened about 2 years ago
by
redstar6486
Conserve formating across translation...
#16 opened over 2 years ago
by
WCDR
Number alter issue
1
#15 opened over 2 years ago
by
sarahai
Make 8 bit quantized model version
3
#14 opened over 2 years ago
by
nonetrix
Translation of longer texts
3
#13 opened over 2 years ago
by
hanshupe
quantized version as app
4
#11 opened over 2 years ago
by
sarahai