LLM EXPLORER 59,420 MODELS INDEXED

Quokka 2.7B by Corianas

By Corianas · 56 downloads
HF Repo ↗ Copy URL

Quokka 2.7B is an open-source language model by Corianas. Features: 2.7b LLM, VRAM: 5.4GB, License: apache-2.0, LLM Explorer Score: 0.12, Arc: 31.1, HellaSwag: 47.7, MMLU: 24.8, GSM8K: 0.4.

  Arxiv:1910.09700   Dataset:guanaco/guanaco   Dataset:the pile   En   Endpoints compatible   Gpt2   Pytorch   Region:us   Safetensors   Tensorboard
Model Card on HF 🤗: https://huggingface.co/Corianas/Quokka_2.7b 

Quokka 2.7B Parameters and Internals

Use Cases 
Primary Use Cases:
Chatbot
Limitations:
Not suitable for accurate information, Do not use for medical or financial advice
Additional Notes 
The model is a fine-tuned version of the existing Cerebras model, trained to follow instructions with a focus on conversational output. Its factual reliability is low.
Supported Languages 
en (unknown)
Training Details 
Data Sources:
the_pile, guanaco/guanaco
Methodology:
Finetuned using DataBricks Dolly training tools
Hardware Used:
8xA100s
LLM NameQuokka 2.7B
Repository 🤗https://huggingface.co/Corianas/Quokka_2.7b 
Model Size2.7b
Required VRAM5.4 GB
Updated2026-08-25
MaintainerCorianas
Model Typegpt2
Model Files  5.4 GB   5.4 GB   0.0 GB
Supported Languagesen
Model ArchitectureGPT2LMHeadModel
Licenseapache-2.0
Transformers Version4.25.1
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token<|endoftext|>
End of Sentence Token<|endoftext|>
Unk Token<|endoftext|>
Vocabulary Size50260
Torch Data Typebfloat16
Activation Functiongelu
Errorsreplace

Best Alternatives to Quokka 2.7B

Best Alternatives
Context / RAM
Downloads
Likes
Cerebras GPT 2.7B Alpaca SP0K / 5.4 GB11310