LLM EXPLORER 59,516 MODELS INDEXED

OLMo 1B by allenai

By allenai · 670 downloads
HF Repo ↗ Copy URL

OLMo 1B is an open-source language model by allenai. Features: 1b LLM, VRAM: 4.7GB, License: apache-2.0, LLM Explorer Score: 0.25, ELO: 1329.

  Arxiv:2302.13971   Arxiv:2402.00838   Custom code   Dataset:allenai/dolma   En   Hf olmo   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/allenai/OLMo-1B 

OLMo 1B Benchmarks

LMSys ELO 1329 vs 1272 (so35) 4.5%
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

OLMo 1B Parameters and Internals

Model Type 
Transformer, autoregressive language model
Additional Notes 
The OLMo models are designed for language modeling with a series of checkpoints available for tracking training progress. Performance varies across benchmarks when compared to peers.
Supported Languages 
English (proficient)
Training Details 
Data Sources:
allenai/dolma
Data Volume:
3 Trillion Tokens
Context Length:
2048
Hardware Used:
LUMI supercomputer MI250X GPUs, MosaicML A100-40GB GPUs
Model Architecture:
Transformer
Input Output 
Input Format:
tokenized text
Accepted Modalities:
text
Output Format:
generated text sequence
LLM NameOLMo 1B
Repository 🤗https://huggingface.co/allenai/OLMo-1B 
Model Size1b
Required VRAM4.7 GB
Updated2026-07-07
Maintainerallenai
Model Typehf_olmo
Model Files  4.7 GB   4.7 GB
Supported Languagesen
Model ArchitectureOLMoForCausalLM
Licenseapache-2.0
Transformers Version4.37.1
Tokenizer ClassOLMoTokenizer
Padding Token<|padding|>
Vocabulary Size50280

Best Alternatives to OLMo 1B

Best Alternatives
Context / RAM
Downloads
Likes
MolmoE 1B 092432K / 28.9 GB1486157
OLMo 1B Instruct Alpaca Amc0K / 2.4 GB95