Frederik s
Create README.md
0e07f36
|
raw
history blame
1.22 kB
metadata
language:
  - multilingual
  - af
  - am
  - ar
  - ast
  - az
  - ba
  - be
  - bg
  - bn
  - br
  - bs
  - ca
  - ceb
  - cs
  - cy
  - da
  - de
  - el
  - en
  - es
  - et
  - fa
  - ff
  - fi
  - fr
  - fy
  - ga
  - gd
  - gl
  - gu
  - ha
  - he
  - hi
  - hr
  - ht
  - hu
  - hy
  - id
  - ig
  - ilo
  - is
  - it
  - ja
  - jv
  - ka
  - kk
  - km
  - kn
  - ko
  - lb
  - lg
  - ln
  - lo
  - lt
  - lv
  - mg
  - mk
  - ml
  - mn
  - mr
  - ms
  - my
  - ne
  - nl
  - 'no'
  - ns
  - oc
  - or
  - pa
  - pl
  - ps
  - pt
  - ro
  - ru
  - sd
  - si
  - sk
  - sl
  - so
  - sq
  - sr
  - ss
  - su
  - sv
  - sw
  - ta
  - th
  - tl
  - tn
  - tr
  - uk
  - ur
  - uz
  - vi
  - wo
  - xh
  - yi
  - yo
  - zh
  - zu
license: mit

https://huggingface.co/facebook/m2m100_1.2B
https://github.com/facebookresearch/fairseq/tree/nllb/examples/m2m_100

ct2-fairseq-converter --data_dir . --model_path 1.2B_last_checkpoint.pt --fixed_dictionary model_dict.128k.txt --quantization int8 --output_dir converted/m2m_100_1.2b_ct2_int8

External language dictionary is not provided; use lang-pairs to infer the set of supported languages. The language ordering is not stable which might cause misalignment in pretraining and finetuning.

wget https://dl.fbaipublicfiles.com/m2m_100/model_dict.128k.txt

# 1.2B parameter model
wget https://dl.fbaipublicfiles.com/m2m_100/1.2B_last_checkpoint.pt