Ct2fast M2m100 1.2B by michaelfeil

 ยป  All LLMs  ยป  michaelfeil  ยป  Ct2fast M2m100 1.2B   URL Share it on

  Arxiv:2010.11125   Af   Am   Ar   Ast   Az   Ba   Be   Bg   Bn   Br   Bs   Ca   Ceb   Cs   Ctranslate2   Cy   Da   De   El   En   Endpoints compatible   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   Multilingual   My   Ne   Nl   No   Ns   Oc   Or   Pa   Pl   Ps   Pt   Region:us   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

Ct2fast M2m100 1.2B Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Ct2fast M2m100 1.2B (michaelfeil/ct2fast-m2m100_1.2B)
๐ŸŒŸ Advertise your project ๐Ÿš€

Ct2fast M2m100 1.2B Parameters and Internals

Model Type 
multilingual, machine translation
Additional Notes 
M2M100 can translate directly between 9,900 direction pairs of 100 languages. Requires `sentencepiece` for tokenization.
Supported Languages 
af (Afrikaans), am (Amharic), ar (Arabic), ast (Asturian), az (Azerbaijani), ba (Bashkir), be (Belarusian), bg (Bulgarian), bn (Bengali), br (Breton), bs (Bosnian), ca (Catalan; Valencian), ceb (Cebuano), cs (Czech), cy (Welsh), da (Danish), de (German), el (Greeek), en (English), es (Spanish), et (Estonian), fa (Persian), ff (Fulah), fi (Finnish), fr (French), fy (Western Frisian), ga (Irish), gd (Gaelic; Scottish Gaelic), gl (Galician), gu (Gujarati), ha (Hausa), he (Hebrew), hi (Hindi), hr (Croatian), ht (Haitian; Haitian Creole), hu (Hungarian), hy (Armenian), id (Indonesian), ig (Igbo), ilo (Iloko), is (Icelandic), it (Italian), ja (Japanese), jv (Javanese), ka (Georgian), kk (Kazakh), km (Central Khmer), kn (Kannada), ko (Korean), lb (Luxembourgish; Letzeburgesch), lg (Ganda), ln (Lingala), lo (Lao), lt (Lithuanian), lv (Latvian), mg (Malagasy), mk (Macedonian), ml (Malayalam), mn (Mongolian), mr (Marathi), ms (Malay), my (Burmese), ne (Nepali), nl (Dutch; Flemish), no (Norwegian), ns (Northern Sotho), oc (Occitan (post 1500)), or (Oriya), pa (Panjabi; Punjabi), pl (Polish), ps (Pushto; Pashto), pt (Portuguese), ro (Romanian; Moldavian; Moldovan), ru (Russian), sd (Sindhi), si (Sinhala; Sinhalese), sk (Slovak), sl (Slovenian), so (Somali), sq (Albanian), sr (Serbian), ss (Swati), su (Sundanese), sv (Swedish), sw (Swahili), ta (Tamil), th (Thai), tl (Tagalog), tn (Tswana), tr (Turkish), uk (Ukrainian), ur (Urdu), uz (Uzbek), vi (Vietnamese), wo (Wolof), xh (Xhosa), yi (Yiddish), yo (Yoruba), zh (Chinese), zu (Zulu)
Training Details 
Model Architecture:
M2M100 is a multilingual encoder-decoder (seq-to-seq) model trained for Many-to-Many multilingual translation.
Input Output 
Input Format:
Tokens
Accepted Modalities:
text
Output Format:
Tokens/Translated Text
Performance Tips:
Use int8 inference for speedup on supported devices.
LLM NameCt2fast M2m100 1.2B
Repository ๐Ÿค—https://huggingface.co/michaelfeil/ct2fast-m2m100_1.2B 
Model Size1.2b
Required VRAM2.5 GB
Updated2025-08-17
Maintainermichaelfeil
Model Files  2.5 GB
Supported Languagesaf am ar az ba be bg bn br bs ca 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 is it ja jv ka kk km kn ko lb lg ln lo lt lv mg mk ml mn mr ms my ne nl 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
Model ArchitectureAutoModel
Licensemit
Padding Token<pad>

Best Alternatives to Ct2fast M2m100 1.2B

Best Alternatives
Context / RAM
Downloads
Likes
Imagebind Huge0K / 4.8 GB9720
Note: green Score (e.g. "73.2") means that the model is better than michaelfeil/ct2fast-m2m100_1.2B.

Rank the Ct2fast M2m100 1.2B Capabilities

๐Ÿ†˜ Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! ๐ŸŒŸ

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 50723 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124