LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Xglm 564M by facebook

 »  All LLMs  »  facebook  »  Xglm 564M   URL Share it on

  16770   
  Arxiv:2112.10668   Ar   Autotrain compatible   Bg   Bn   Ca   De   El   En   Es   Et   Eu   Fi   Fr   Hi   Ht   Id   It   Ja   Jax   Ko   Multilingual   My   Pt   Pytorch   Qu   Region:us   Ru   Sw   Ta   Te   Tf   Th   Tr   Ur   Vi   Xglm   Zh
Model Card on HF 🤗: https://huggingface.co/facebook/xglm-564M 

Xglm 564M Benchmarks

ARC: 24.57 vs 96.7 (so35)-74.6%
HellaSwag: 34.64 vs 95.3 (gpt4)-63.7%
MMLU: 25.18 vs 88.3 (so35)-71.5%
TruthfulQA: 40.43 vs 59 (gpt4)-31.5%
WinoGrande: 52.25 vs 87.5 (gpt4)-40.3%
GSM8K: 0.23 vs 96.4 (so35)-99.8%
LLME Score: 0.08589
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Xglm 564M (facebook/xglm-564M)
🌟 Advertise your project 🚀

Xglm 564M Parameters and Internals

Model Type 
multilingual, autoregressive, language model
Supported Languages 
en (Indo-European), ru (Indo-European), zh (Sino-Tibetan), de (Indo-European), es (Indo-European), fr (Indo-European), ja (Japonic), it (Indo-European), pt (Indo-European), el (Indo-European), ko (Koreanic), fi (Uralic), id (Austronesian), tr (Turkic), ar (Afro-Asiatic), vi (Austroasiatic), th (Tai–Kadai), bg (Indo-European), ca (Indo-European), hi (Indo-European), et (Uralic), bn (Indo-European), ta (Dravidian), ur (Indo-European), sw (Niger–Congo), te (Dravidian), eu (Language isolate), my (Sino-Tibetan), ht (Creole), qu (Quechuan)
Training Details 
Data Sources:
30 languages corpus
Data Volume:
500 billion sub-tokens
Model Architecture:
multilingual autoregressive model with 564M parameters
LLM NameXglm 564M
Repository 🤗https://huggingface.co/facebook/xglm-564M 
Model Size564m
Required VRAM1.1 GB
Updated2025-09-23
Maintainerfacebook
Model Typexglm
Model Files  1.1 GB
Supported Languagesen ru zh de es fr ja it pt el ko fi id tr ar vi th bg ca hi et bn ta ur sw te eu my ht qu
Model ArchitectureXGLMForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.16.0.dev0
Tokenizer ClassXGLMTokenizer
Padding Token<pad>
Vocabulary Size256008
Activation Functiongelu

Best Alternatives to Xglm 564M

Best Alternatives
Context / RAM
Downloads
Likes
KarveeYaknon2K / 2.3 GB50
Note: green Score (e.g. "73.2") means that the model is better than facebook/xglm-564M.

Rank the Xglm 564M Capabilities

🆘 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! 🌟

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? 51534 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124
  Support LLM Explorer