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

Galactica 6.7B by facebook

 »  All LLMs  »  facebook  »  Galactica 6.7B   URL Share it on

  1291   
  Arxiv:1810.03993   Autotrain compatible   Galactica   Opt   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/facebook/galactica-6.7b 

Galactica 6.7B Benchmarks

LLME Score: 0.0661
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Galactica 6.7B (facebook/galactica-6.7b)
🌟 Advertise your project 🚀

Galactica 6.7B Parameters and Internals

Model Type 
Transformer based architecture, decoder-only setup
Use Cases 
Areas:
scientific domain, mathematics, biology, chemistry
Primary Use Cases:
citation prediction, scientific QA, mathematical reasoning, summarization, document generation, molecular property prediction, entity extraction
Limitations:
prone to hallucination, popularity bias, exhibits bias on certain measures
Considerations:
Being aware of hallucination and biases is important.
Training Details 
Data Sources:
papers, textbooks, scientific websites, encyclopedias, reference material, knowledge bases
Data Volume:
106 billion tokens
Model Architecture:
Transformer based architecture in a decoder-only setup with a few modifications
Release Notes 
Date:
November 2022
LLM NameGalactica 6.7B
Repository 🤗https://huggingface.co/facebook/galactica-6.7b 
Model Size6.7b
Required VRAM13.8 GB
Updated2025-09-23
Maintainerfacebook
Model Typeopt
Model Files  10.0 GB: 1-of-2   3.8 GB: 2-of-2
Model ArchitectureOPTForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.21.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size50000
Torch Data Typefloat16
Activation Functiongelu

Best Alternatives to Galactica 6.7B

Best Alternatives
Context / RAM
Downloads
Likes
....7B Qcqa Ub 16 Best For Q Loss2K / 27.4 GB50
...B Qcqa Ub 16 Best For KV Cache2K / 27.4 GB50
...7B Gqa Ub 16 Best For KV Cache2K / 27.4 GB50
Galactica 6.7B EssayWriter2K / 13.4 GB18275
Galactica 6.7B ReFT GSM8k2K / 13.8 GB50
Opt Flan Iml 6.7B2K / 26.6 GB9681
...lactica 6.7B Evol Instruct 70K2K / 27.4 GB183519
OPT 6.7B Nerybus Mix2K / 13.7 GB186920
Galactica 6.7B Finetuned2K / 27.4 GB166934
Opt 6.7B2K / 13.4 GB25868118
Note: green Score (e.g. "73.2") means that the model is better than facebook/galactica-6.7b.

Rank the Galactica 6.7B 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? 51539 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