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

Aira 2 355M by nicholasKluge

 »  All LLMs  »  nicholasKluge  »  Aira 2 355M   URL Share it on

  10   
  Arxiv:1803.05457   Arxiv:2109.07958   Arxiv:2203.09509   Alignment   Assistant   Autotrain compatible Base model:finetune:openai-com... Base model:openai-community/gp...   Co2 eq emissions   Conversation Dataset:nicholaskluge/instruct...   En   Endpoints compatible   Gpt2   Instruct   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/nicholasKluge/Aira-2-355M 

Aira 2 355M Benchmarks

ARC: 27.56 vs 96.7 (so35)-71.5%
HellaSwag: 38.92 vs 95.3 (gpt4)-59.2%
MMLU: 27.26 vs 88.3 (so35)-69.1%
TruthfulQA: 38.53 vs 59 (gpt4)-34.7%
WinoGrande: 53.75 vs 87.5 (gpt4)-38.6%
LLME Score: 0.13406
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aira 2 355M (nicholasKluge/Aira-2-355M)
🌟 Advertise your project 🚀

Aira 2 355M Parameters and Internals

Model Type 
text generation, instruction tuned, conversation, assistant
Use Cases 
Areas:
research, commercial applications
Applications:
instruction following, text generation, virtual assistance
Primary Use Cases:
interactive dialogues, instruction response
Limitations:
May produce hallucinations, biases, toxic content, Repetition and verbosity issues
Supported Languages 
English (Primary)
Training Details 
Data Sources:
Instruct-Aira Dataset
Methodology:
fine-tuning
Hardware Used:
1 NVIDIA A100-SXM4-40GB
Input Output 
Input Format:
Use special tokens <|startofinstruction|>, <|endofinstruction|>
Accepted Modalities:
text
Output Format:
Generated text response
Performance Tips:
Avoid repetition penalty set to a low value to prevent loops
LLM NameAira 2 355M
Repository 🤗https://huggingface.co/nicholasKluge/Aira-2-355M 
Base Model(s)  gpt2-medium   /gpt2-medium
Model Size355m
Required VRAM0 GB
Updated2025-09-23
MaintainernicholasKluge
Model Typegpt2
Instruction-BasedYes
Model Files  1.4 GB   1.0 GB   1.4 GB   0.0 GB   0.0 GB
Supported Languagesen
Model ArchitectureGPT2LMHeadModel
Licenseapache-2.0
Model Max Length1024
Transformers Version4.33.1
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|startofinstruction|>
End of Sentence Token<|endofcompletion|>
Unk Token<|endoftext|>
Vocabulary Size50261
Torch Data Typefloat32
Activation Functiongelu_new
Errorsreplace

Best Alternatives to Aira 2 355M

Best Alternatives
Context / RAM
Downloads
Likes
SSH 355M0K / 1.4 GB1260
Note: green Score (e.g. "73.2") means that the model is better than nicholasKluge/Aira-2-355M.

Rank the Aira 2 355M 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? 51618 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