LLM EXPLORER 59,420 MODELS INDEXED

Open Calm Large by cyberagent

By cyberagent · 1346 downloads
HF Repo ↗ Copy URL

Open Calm Large is an open-source language model by cyberagent. Features: LLM, VRAM: 1.8GB, Context: 2K, License: cc-by-sa-4.0, LLM Explorer Score: 0.13, Arc: 20.7, HellaSwag: 29.6, MMLU: 25.2, GSM8K: 0.1.

  Dataset:cc100   Dataset:mc4   Dataset:wikipedia   Deploy:azure   Gpt neox   Ja   Japanese   Pytorch   Region:us
Model Card on HF 🤗: https://huggingface.co/cyberagent/open-calm-large 

Open Calm Large Parameters and Internals

Model Type 
Transformer-based Language Model
Use Cases 
Areas:
Japanese Text Generation
Additional Notes 
The model is part of a suite of language models and is implemented using the GPT-NeoX library. The OpenCALM-Large model is specifically designed for Japanese language tasks.
Supported Languages 
Japanese (Full)
Training Details 
Data Sources:
Wikipedia (ja), Common Crawl (ja)
Model Architecture:
Decoder-only
LLM NameOpen Calm Large
Repository 🤗https://huggingface.co/cyberagent/open-calm-large 
Required VRAM1.8 GB
Updated2026-07-09
Maintainercyberagent
Model Typegpt_neox
Model Files  1.8 GB
Supported Languagesja
Model ArchitectureGPTNeoXForCausalLM
Licensecc-by-sa-4.0
Context Length2048
Model Max Length2048
Transformers Version4.27.0.dev0
Tokenizer ClassGPTNeoXTokenizer
Padding Token<|padding|>
Vocabulary Size52096
Torch Data Typefloat16

Best Alternatives to Open Calm Large

Best Alternatives
Context / RAM
Downloads
Likes
Catlm8K / 7.8 GB144
...Prover 14final Checkpoint 58304K / 14.9 GB60
Neox Musenet Untrained4K / 7.3 GB60
Stabillm Instruct De4K / 31.8 GB70
MusePy 1 12K / 0.7 GB251
MonoCoder OMP2K / 3.6 GB130
ProofGPT V0.12K / 2.9 GB763
KULLM RLHF2K / 25.8 GB113
Open Calm Small2K / 0.4 GB221420
Step3 Mk72K / 25.8 GB70
Note: green Score (e.g. "73.2") means that the model is better than cyberagent/open-calm-large.