Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets
  • Docs
  • Enterprise
  • Pricing
    • Website
      • Tasks
      • HuggingChat
      • Collections
      • Languages
      • Organizations
    • Community
      • Blog
      • Posts
      • Daily Papers
      • Hardware
      • Learn
      • Discord
      • Forum
      • GitHub
    • Solutions
      • Team & Enterprise
      • Hugging Face PRO
      • Enterprise Support
      • Inference Providers
      • Inference Endpoints
      • Storage Buckets

  • Log In
  • Sign Up

jvonrad
/
alignment-without-transfer

multilingual
pretraining
tokenization
cross-lingual-transfer
xscript-pretraining
Model card Files Files and versions
xet
Community
1
alignment-without-transfer
2.58 TB
Ctrl+K
Ctrl+K
  • 1 contributor
History: 1,510 commits
jvonrad's picture
jvonrad
Model card: naming scheme, LR state, loading, checkpoint table
0d77e0c verified about 2 hours ago
  • runs
    en-zh__unigram_bi_zh: full snapshot archive 2 months ago
  • src
    Upload src/xscript/train.py with huggingface_hub 4 months ago
  • tokenizers
    tokenizer unigram_bi_zh 2 months ago
  • .gitattributes
    70.2 kB
    en-zh-bi-23b: checkpoint 2 months ago
  • README.md
    31.1 kB
    Model card: naming scheme, LR state, loading, checkpoint table about 2 hours ago
  • models.json
    24.7 kB
    models.json: +6 (en-zh-bi, en-zh-bi-2b, en-zh-bi-5b, en-zh-bi-10b, en-zh-bi-15b, en-zh-bi-23b) 2 months ago
  • requirements.txt
    281 Bytes
    Upload requirements.txt with huggingface_hub 4 months ago
  • run_benchmarks.py
    5.7 kB
    Upload run_benchmarks.py with huggingface_hub 4 months ago