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

Pythia 70M ChatSalad by concedo

 »  All LLMs  »  concedo  »  Pythia 70M ChatSalad   URL Share it on

  1919   
  Autotrain compatible   En   Gpt neox   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/concedo/Pythia-70M-ChatSalad 

Pythia 70M ChatSalad Benchmarks

ARC: 20.99 vs 96.7 (so35)-78.3%
HellaSwag: 27.28 vs 95.3 (gpt4)-71.4%
MMLU: 24.78 vs 88.3 (so35)-71.9%
TruthfulQA: 49.74 vs 59 (gpt4)-15.7%
WinoGrande: 52.41 vs 87.5 (gpt4)-40.1%
LLME Score: 0.12702
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Pythia 70M ChatSalad (concedo/Pythia-70M-ChatSalad)
🌟 Advertise your project 🚀

Pythia 70M ChatSalad Parameters and Internals

Additional Notes 
This model is a follow-up finetune intended to improve coherence.
Supported Languages 
en (unknown)
Training Details 
Data Sources:
same dataset as OPT-19M-ChatSalad
Methodology:
Finetune
LLM NamePythia 70M ChatSalad
Repository 🤗https://huggingface.co/concedo/Pythia-70M-ChatSalad 
Model Size70m
Required VRAM0.2 GB
Updated2025-09-23
Maintainerconcedo
Model Typegpt_neox
Model Files  0.2 GB   0.2 GB
Supported Languagesen
Model ArchitectureGPTNeoXForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.24.0
Tokenizer ClassGPTNeoXTokenizer
Vocabulary Size50278
Torch Data Typefloat16

Best Alternatives to Pythia 70M ChatSalad

Best Alternatives
Context / RAM
Downloads
Likes
Pythia 70m Sft Hh2K / 0.1 GB60
Pythia 70M Deduped2K / 0.2 GB38589325
Pythia 70M Multi2K / 0.3 GB60
Pythia 70M2K / 0.2 GB16422273
Pythia Chinese 70M UDN2K / 0.2 GB180
Pythia 70m Sft2K / 0.3 GB50
...ythia 70M Wikipedia Paragraphs2K / 0.3 GB43
...a 70M Deduped Cleansharegpt En2K / 0.3 GB18950
...thia 70M Deduped Cleansharegpt2K / 0.3 GB12611
...ythia 70M Deduped Step44k 92bt2K / 0.2 GB18370
Note: green Score (e.g. "73.2") means that the model is better than concedo/Pythia-70M-ChatSalad.

Rank the Pythia 70M ChatSalad 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? 51544 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