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

OLMo 7B Hf by allenai

 »  All LLMs  »  allenai  »  OLMo 7B Hf   URL Share it on

  10848   
  Arxiv:2302.13971   Arxiv:2402.00838   Autotrain compatible   Dataset:allenai/dolma   En   Endpoints compatible   Olmo   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/allenai/OLMo-7B-hf 

OLMo 7B Hf Benchmarks

MMLU Pro: 1.92
GPQA: 3.02
MUSR: 2.08
BBH: 5.76
IFEval: 27.19 vs 88 (so35)-69.1%
ARC: 45.65 vs 96.7 (so35)-52.8%
HellaSwag: 77.31 vs 95.3 (gpt4)-18.9%
MMLU: 28.13 vs 88.3 (so35)-68.1%
TruthfulQA: 35.93 vs 59 (gpt4)-39.1%
WinoGrande: 69.38 vs 87.5 (gpt4)-20.7%
GSM8K: 3.79 vs 96.4 (so35)-96.1%
MATH Lvl 5: 1.21
LLME Score: 0.2649
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
OLMo 7B Hf (allenai/OLMo-7B-hf)

OLMo 7B Hf Parameters and Internals

Model Type 
Transformer style autoregressive language model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Natural language processing tasks
Primary Use Cases:
Language modeling, Text generation
Limitations:
May produce harmful or biased content
Considerations:
User awareness of potential risks and limitations.
Additional Notes 
Model checkpoints and code are open-source.
Supported Languages 
English (High)
Training Details 
Data Sources:
Dolma dataset
Data Volume:
2.5 Trillion Training Tokens
Methodology:
Sequential Block Transformer with SwiGLU activation and RoPE positional embeddings
Context Length:
2048
Hardware Used:
MI250X GPUs at LUMI supercomputer, A100-40GB GPUs provided by MosaicML
Model Architecture:
Transformer model with 32 layers, 4096 hidden size, 32 attention heads, sequential block type
Safety Evaluation 
Risk Categories:
Harmful content, Sensitive content, Bias
Ethical Considerations:
Model can generate harmful and biased content.
Responsible Ai Considerations 
Fairness:
Potential bias in language outputs.
Transparency:
Open-source model with accessible training data details.
Accountability:
Developed by Allen Institute for AI.
Mitigation Strategies:
Awareness of risks and user guidelines.
Input Output 
Input Format:
Text prompts
Accepted Modalities:
Text
Output Format:
Generated text
Performance Tips:
Use optimized settings for text generation speed and accuracy.
Release Notes 
Version:
7B
Notes:
Initial release for open language modeling.
LLM NameOLMo 7B Hf
Repository 🤗https://huggingface.co/allenai/OLMo-7B-hf 
Model Size7b
Required VRAM27.6 GB
Updated2025-06-01
Maintainerallenai
Model Typeolmo
Model Files  4.9 GB: 1-of-6   5.0 GB: 2-of-6   4.9 GB: 3-of-6   4.9 GB: 4-of-6   4.9 GB: 5-of-6   3.0 GB: 6-of-6
Supported Languagesen
Model ArchitectureOlmoForCausalLM
Licenseapache-2.0
Context Length2048
Model Max Length2048
Transformers Version4.40.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|padding|>
Vocabulary Size50304
Torch Data Typefloat32

Best Alternatives to OLMo 7B Hf

Best Alternatives
Context / RAM
Downloads
Likes
OLMo 1.7 7B Hf4K / 27.6 GB263798
OLMo 7B 0724 Instruct Hf4K / 13.8 GB36626
OLMo 7B 0724 Hf4K / 27.6 GB189513
OLMo 7B 0424 Hf4K / 27.6 GB115512
OLMo 7B Instruct Hf2K / 27.6 GB17206
OLMo 7B 0724 SFT Hf2K / 13.8 GB30004
OLMo 7B Twin 2T Hf2K / 27.6 GB7881
OLMo 7B SFT Hf2K / 27.6 GB1080
Olmo 7B Hf Step02K / 27.6 GB90
OLMo 7B Instruct Hf2K / 27.6 GB133

Rank the OLMo 7B Hf 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? 47770 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 v20241227
  Support LLM Explorer