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

Sheared LLaMA 2.7B by princeton-nlp

 »  All LLMs  »  princeton-nlp  »  Sheared LLaMA 2.7B   URL Share it on

  1838   
  Arxiv:2310.06694   Autotrain compatible   Endpoints compatible   Llama   Pytorch   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B 

Sheared LLaMA 2.7B Benchmarks

MMLU Pro: 2.08
GPQA: 3.36
MUSR: 2.09
BBH: 5.66
IFEval: 24.17 vs 88 (so35)-72.5%
ARC: 41.72 vs 96.7 (so35)-56.9%
HellaSwag: 71.01 vs 95.3 (gpt4)-25.5%
MMLU: 26.92 vs 88.3 (so35)-69.5%
TruthfulQA: 37.32 vs 59 (gpt4)-36.7%
WinoGrande: 67.01 vs 87.5 (gpt4)-23.4%
GSM8K: 1.06 vs 96.4 (so35)-98.9%
MATH Lvl 5: 1.28
LLME Score: 0.18916
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Sheared LLaMA 2.7B (princeton-nlp/Sheared-LLaMA-2.7B)
🌟 Advertise your project 🚀

Sheared LLaMA 2.7B Parameters and Internals

Model Type 
language model
Use Cases 
Areas:
research, commercial applications
Applications:
reasoning, reading comprehension, language modeling, knowledge intensive tasks
Primary Use Cases:
Various NLP tasks and evaluations based on extensive downstream task metrics.
Additional Notes 
Dynamically loads data from different domains during pre-training. Pruned and further pre-trained from meta-llama/Llama-2-7b-hf.
Training Details 
Data Sources:
RedPajama dataset
Data Volume:
50 billion tokens
Methodology:
Structured pruning and continued pre-training
LLM NameSheared LLaMA 2.7B
Repository 🤗https://huggingface.co/princeton-nlp/Sheared-LLaMA-2.7B 
Model Size2.7b
Required VRAM10.8 GB
Updated2025-09-10
Maintainerprinceton-nlp
Model Typellama
Model Files  9.9 GB: 1-of-2   0.9 GB: 2-of-2
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat32

Best Alternatives to Sheared LLaMA 2.7B

Best Alternatives
Context / RAM
Downloads
Likes
Dopeyshearedplats 2.7B V14K / 5.7 GB18072
Shearedplats 2.7B V24K / 5.7 GB24612
...redplats 2.7B V2 Instruct V0.14K / 5.4 GB63
Llama Final4K / 5.5 GB60
DPO VinaLlama Completed4K / 5.6 GB50
Urllm Ko En 2.7B4K / 11.2 GB60
Sheared LLaMA 2.7B Pruned4K / 5.4 GB11133
Vinallama 2.7B Chat4K / 5.5 GB147416
...heared Llama 2.7B Deita 6K Sft4K / 5.4 GB71
Vinallama 2.7B4K / 5.5 GB112013

Rank the Sheared LLaMA 2.7B 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? 51262 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