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 Evol Instruct 70K by GeorgiaTechResearchInstitute

 »  All LLMs  »  GeorgiaTechResearchInstitute  »  Galactica 6.7B Evol Instruct 70K   URL Share it on

  1244   
  Arxiv:2304.12244   Alpaca   Autotrain compatible Dataset:victor123/evol instruc...   Galactica   Instruct   Opt   Pytorch   Region:us   Sharded   Wizardlm
Model Card on HF 🤗: https://huggingface.co/GeorgiaTechResearchInstitute/galactica-6.7b-evol-instruct-70k 

Galactica 6.7B Evol Instruct 70K Benchmarks

ARC: 42.58 vs 96.7 (so35)-56%
HellaSwag: 49.3 vs 95.3 (gpt4)-48.3%
MMLU: 32.96 vs 88.3 (so35)-62.7%
TruthfulQA: 42.1 vs 59 (gpt4)-28.6%
WinoGrande: 56.27 vs 87.5 (gpt4)-35.7%
GSM8K: 0.38 vs 96.4 (so35)-99.6%
LLME Score: 0.16409
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 Evol Instruct 70K (GeorgiaTechResearchInstitute/galactica-6.7b-evol-instruct-70k)

Galactica 6.7B Evol Instruct 70K Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research
Applications:
Scientific tasks, Language models applied to scientific domain
Limitations:
Cautions against production use without safeguards
Training Details 
Data Sources:
Papers, Textbooks, Scientific websites, Encyclopedias
Data Volume:
106 billion tokens
Methodology:
Fine-tuning on Evol-Instruct-70k dataset
Context Length:
2048
Training Time:
22 hours
Hardware Used:
8 A100 80GB GPUs
Input Output 
Input Format:
Instruction-response prompt
Accepted Modalities:
Text
Output Format:
Text-based responses
LLM NameGalactica 6.7B Evol Instruct 70K
Repository 🤗https://huggingface.co/GeorgiaTechResearchInstitute/galactica-6.7b-evol-instruct-70k 
Model Size6.7b
Required VRAM27.4 GB
Updated2024-12-22
MaintainerGeorgiaTechResearchInstitute
Model Typeopt
Instruction-BasedYes
Model Files  10.0 GB: 1-of-3   9.9 GB: 2-of-3   7.5 GB: 3-of-3   0.0 GB
Model ArchitectureOPTForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.28.0.dev0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size50000
Torch Data Typefloat32
Activation Functiongelu

Best Alternatives to Galactica 6.7B Evol Instruct 70K

Best Alternatives
Context / RAM
Downloads
Likes
Galactica 6.7B EssayWriter2K / 13.4 GB11563
Opt Flan Iml 6.7B2K / 26.6 GB12491
OPI Galactica 6.7B2K / 13.4 GB5614
Ev Glaive Math12K / 27.4 GB110
Ev Glaive Math2K / 27.4 GB100
Open Instruct Opt 6.7B Tulu2K / 26.6 GB252
LongForm OPT 6.7B2K / 13.3 GB214
...PT 6.7B Erebus Instruct Follow2K / 13.8 GB163
Note: green Score (e.g. "73.2") means that the model is better than GeorgiaTechResearchInstitute/galactica-6.7b-evol-instruct-70k.

Rank the Galactica 6.7B Evol Instruct 70K 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? 40066 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 v20241217
  Support LLM Explorer