Who developed Aira 2 774M and how large is it?

Aira 2 774M is developed by nicholasKluge, a model with 774m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

How does Aira 2 774M perform on standard benchmarks?

Aira 2 774M has the following published scores: MMLU 25.1. Compare against reference models on this page or on the LLM Explorer leaderboards.

Aira 2 774M by nicholasKluge

Name: Aira 2 774M
Author: nicholasKluge

Aira 2 774M is an open-source language model by nicholasKluge. Features: 774m LLM, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.13, Arc: 28.8, HellaSwag: 40.8, MMLU: 25.1.

Arxiv:1803.05457 Arxiv:2109.07958 Arxiv:2203.09509 Alignment Assistant 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-2-774M

Aira 2 774M Benchmarks

ARC: 28.75 vs 96.7 (so35)^-70.3%

HellaSwag: 40.8 vs 95.3 (gpt4)^-57.2%

MMLU: 25.1 vs 88.3 (so35)^-71.6%

LLME Score: 0.13061

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Aira 2 774M Parameters and Internals

Model Type

instruction-tuned, text generation, conversation, assistant

Additional Notes

This model is susceptible to hallucinations, biases, and repetition issues.

Supported Languages

en (English proficiency demonstrated)

Training Details

Data Sources:

nicholasKluge/instruct-aira-dataset

Methodology:

fine-tuning

Hardware Used:

1 NVIDIA A100-SXM4-40GB

LLM Name	Aira 2 774M
Repository 🤗	https://huggingface.co/nicholasKluge/Aira-2-774M
Base Model(s)	gpt2-large /gpt2-large
Model Size	774m
Required VRAM	0 GB
Updated	2026-05-17
Maintainer	nicholasKluge
Model Type	gpt2
Instruction-Based	Yes
Model Files	3.1 GB 1.9 GB 3.1 GB 0.0 GB 0.0 GB
Supported Languages	en
Model Architecture	GPT2LMHeadModel
License	apache-2.0
Model Max Length	1024
Transformers Version	4.33.2
Tokenizer Class	GPT2Tokenizer
Beginning of Sentence Token	<\|startofinstruction\|>
End of Sentence Token	<\|endofcompletion\|>
Unk Token	<\|endoftext\|>
Vocabulary Size	50261
Torch Data Type	float32
Activation Function	gelu_new
Errors	replace

Best Alternatives to Aira 2 774M

Best Alternatives	Context / RAM	Downloads	Likes
Gpt2 Large Conversational	0K / 1.6 GB	967	4

Rank the Aira 2 774M 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? 54089 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.

Check out Ag3ntum — our secure, self-hosted AI agent for server management.

Release v20260328a

Support LLM Explorer