Instructions to use facebook/nllb-200-3.3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/nllb-200-3.3B 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="facebook/nllb-200-3.3B")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/nllb-200-3.3B") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/nllb-200-3.3B") - Notebooks
- Google Colab
- Kaggle
How to provide the context to the translation
👍 7
#18 opened about 1 year ago
by
deepakpallavalli
Adding `safetensors` variant of this model
#17 opened over 1 year ago
by
SFconvertbot
Can this be quantized/Are there quantized variants available?
#16 opened over 1 year ago
by
popeyed
What are the input variables required for the NLLB model in the inference process
1
#15 opened over 1 year ago
by
LiPengtao12138
language code for Telugu Language
1
#14 opened over 1 year ago
by
dinesh-001
Update README.md with CO2 emissions
#13 opened about 2 years ago
by
m-ric
[AUTOMATED] Model Memory Requirements
#12 opened about 2 years ago
by
model-sizer-bot
[AUTOMATED] Model Memory Requirements
#11 opened about 2 years ago
by
model-sizer-bot
Adding `safetensors` variant of this model
#10 opened over 2 years ago
by
SFconvertbot
how to handle multi-line string
#9 opened over 2 years ago
by
StephennFernandes
Fine tuning model Google Colab t4-GPU
#8 opened over 2 years ago
by
Macs98
Inconsistency between model name and the model architecture from config.json
1
#7 opened over 2 years ago
by
jiang784
Hosting as Inference Endpoint doesn't work
4
#6 opened over 2 years ago
by
charliekocsis
Add multilingual to the language tag
#4 opened over 3 years ago
by
lbourdois
Strange results
👍 4
3
#3 opened over 3 years ago
by
felixduner
Is there a distilled version of this model?
2
#2 opened almost 4 years ago
by
keithhon
model doesn't work in the hosted interface api
2
#1 opened almost 4 years ago
by
labx