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

Pythia 6.9B Deduped 8K by openaccess-ai-collective

 »  All LLMs  »  openaccess-ai-collective  »  Pythia 6.9B Deduped 8K   URL Share it on

  6   
  Arxiv:2101.00027   Arxiv:2201.07311   Autotrain compatible Dataset:eleutherai/the pile de...   En   Endpoints compatible   Ext 8k   Gpt neox   Pythia   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/openaccess-ai-collective/pythia-6.9b-deduped-8k 

Pythia 6.9B Deduped 8K Benchmarks

LLME Score: 0.10507
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pythia 6.9B Deduped 8K (openaccess-ai-collective/pythia-6.9b-deduped-8k)

Pythia 6.9B Deduped 8K Parameters and Internals

Model Type 
Transformer-based Language Model
Use Cases 
Areas:
Research
Primary Use Cases:
Research on behavior, functionality, and limitations of large language models.
Limitations:
Not intended for human-facing interactions; may generate harmful or offensive text., Only suitable for English language; not meant for translation or multilingual text generation.
Additional Notes 
Pythia models were retrained to address hyperparameter discrepancies; old versions are still available but the retrained suite is recommended.
Supported Languages 
English (high)
Training Details 
Data Sources:
The Pile
Data Volume:
299,892,736,000 tokens
Methodology:
Global deduplication was applied to the dataset.
Context Length:
8000
Training Time:
143000 steps
Model Architecture:
Transformer-based
Release Notes 
Version:
Current Release
Date:
January 2023
Notes:
Renamed models, uniform batch size, additional checkpoints, Flash Attention used, remedied learning rate schedule inconsistency.
LLM NamePythia 6.9B Deduped 8K
Repository 🤗https://huggingface.co/openaccess-ai-collective/pythia-6.9b-deduped-8k 
Model Size6.9b
Required VRAM13.8 GB
Updated2025-02-22
Maintaineropenaccess-ai-collective
Model Typegpt_neox
Model Files  10.0 GB: 1-of-2   3.8 GB: 2-of-2
Supported Languagesen
Context Length8k
Model ArchitectureGPTNeoXForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.30.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50304
Torch Data Typebfloat16

Best Alternatives to Pythia 6.9B Deduped 8K

Best Alternatives
Context / RAM
Downloads
Likes
Ppo Tldr 6.9B2K / 13.8 GB80
...I Pythia 6.9B Deduped Sft Tldr2K / 27.4 GB780
...I Pythia 6.9B Deduped Sft Tldr2K / 13.8 GB8250
Pythia 6.9B2K / 13.8 GB9195350
Pythia 6.9B Deduped2K / 13.8 GB119958
Oasst Pythia 6.9B 4000 Steps2K / 13.8 GB19240
Open Instruct Pythia 6.9B Tulu2K / 27.6 GB21925
Pythia 6.9B HC32K / 27.7 GB372
...an Large Pythia 6.9B Dev Phase2K / 27.6 GB73
Pythia 6.9B Deduped Alpaca2K / 27.6 GB71
Note: green Score (e.g. "73.2") means that the model is better than openaccess-ai-collective/pythia-6.9b-deduped-8k.

Rank the Pythia 6.9B Deduped 8K 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? 43470 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 v20241227
  Support LLM Explorer