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

Opt 2.7B Wikitext2 by lnair

 »  All LLMs  »  lnair  »  Opt 2.7B Wikitext2   URL Share it on

  9   
  Autotrain compatible   Dataset:wikitext   Endpoints compatible   Generated from trainer   Opt   Pytorch   Region:us   Sharded   Tensorboard
Model Card on HF 🤗: https://huggingface.co/lnair/opt-2.7b-wikitext2 

Opt 2.7B Wikitext2 Benchmarks

LLME Score: 0.07889
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Opt 2.7B Wikitext2 (lnair/opt-2.7b-wikitext2)
🌟 Advertise your project 🚀

Opt 2.7B Wikitext2 Parameters and Internals

Model Type 
Language Model
Additional Notes 
Training uses Adam optimizer with betas=(0.9,0.999), epsilon=1e-08, learning rate of 3e-05, train and eval batch sizes of 2, using a linear learning rate scheduler over 2 epochs with seed 42.
Training Details 
Data Sources:
wikitext-2-raw-v1
Model Architecture:
Fine-tuned version of the OPT model
LLM NameOpt 2.7B Wikitext2
Repository 🤗https://huggingface.co/lnair/opt-2.7b-wikitext2 
Model Size2.7b
Required VRAM11.1 GB
Updated2025-09-14
Maintainerlnair
Model Typeopt
Model Files  10.0 GB: 1-of-2   1.1 GB: 2-of-2   0.0 GB
Model ArchitectureOPTForCausalLM
Context Length2048
Model Max Length2048
Transformers Version4.27.4
Tokenizer ClassGPT2Tokenizer
Beginning of Sentence Token</s>
End of Sentence Token</s>
Unk Token</s>
Vocabulary Size50272
Torch Data Typefloat32
Activation Functionrelu
Errorsreplace

Best Alternatives to Opt 2.7B Wikitext2

Best Alternatives
Context / RAM
Downloads
Likes
LLmRa 2.7B2K / 10.6 GB6421
OPT 2.7B Nerybus Mix2K / 5.5 GB183210
Opt 2.7B2K / 5.3 GB5931186
OPT 2.7B Erebus2K / 5.3 GB226541
OPT 2.7B Nerys V22K / 5.3 GB16876
Opt 2.7B Realtime Chat V22K / 11.1 GB50
LongForm OPT 2.7B2K / 5.3 GB73
Opt 2.7B Realtime Chat2K / 11.1 GB42
Opt Peter 2.7B2K / 10.6 GB162
Opt 2.7B AWQ2K / 1.6 GB80
Note: green Score (e.g. "73.2") means that the model is better than lnair/opt-2.7b-wikitext2.

Rank the Opt 2.7B Wikitext2 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? 51368 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