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

Stockmark 100B by stockmark

 »  All LLMs  »  stockmark  »  Stockmark 100B   URL Share it on

  1324   
  Autotrain compatible   En   Endpoints compatible   Ja   Llama   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/stockmark/stockmark-100b 

Stockmark 100B Benchmarks

LLME Score: 0.19355
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Stockmark 100B Parameters and Internals

Model Type 
text generation
Additional Notes 
Supported by GENIAC.
Supported Languages 
ja (full), en (full)
Training Details 
Data Sources:
Stockmark Web Corpus, Patent, Wikipedia, mC4, CommonCrawl, RedPajama-Data
Data Volume:
910 billion tokens
Training Time:
7 weeks
Hardware Used:
48 nodes of a3 instances (8*H100) GPUs
Input Output 
Accepted Modalities:
text
Output Format:
text
LLM NameStockmark 100B
Repository 🤗https://huggingface.co/stockmark/stockmark-100b 
Model Size100b
Required VRAM191.9 GB
Updated2025-06-09
Maintainerstockmark
Model Typellama
Model Files  4.8 GB: 1-of-40   4.9 GB: 2-of-40   4.7 GB: 3-of-40   4.9 GB: 4-of-40   4.9 GB: 5-of-40   4.9 GB: 6-of-40   4.7 GB: 7-of-40   4.9 GB: 8-of-40   4.9 GB: 9-of-40   4.9 GB: 10-of-40   4.7 GB: 11-of-40   4.9 GB: 12-of-40   4.9 GB: 13-of-40   4.9 GB: 14-of-40   4.7 GB: 15-of-40   4.9 GB: 16-of-40   4.9 GB: 17-of-40   4.9 GB: 18-of-40   4.7 GB: 19-of-40   4.9 GB: 20-of-40   4.9 GB: 21-of-40   4.9 GB: 22-of-40   4.7 GB: 23-of-40   4.9 GB: 24-of-40   4.9 GB: 25-of-40   4.9 GB: 26-of-40   4.7 GB: 27-of-40   4.9 GB: 28-of-40   4.9 GB: 29-of-40   4.9 GB: 30-of-40   4.7 GB: 31-of-40   4.9 GB: 32-of-40   4.9 GB: 33-of-40   4.9 GB: 34-of-40   4.7 GB: 35-of-40   4.9 GB: 36-of-40   4.9 GB: 37-of-40   4.9 GB: 38-of-40   4.7 GB: 39-of-40   2.9 GB: 40-of-40
Supported Languagesja en
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length4096
Model Max Length4096
Transformers Version4.40.1
Tokenizer ClassLlamaTokenizer
Padding Token<pad>
Vocabulary Size60416
Torch Data Typebfloat16
Stockmark 100B (stockmark/stockmark-100b)

Best Alternatives to Stockmark 100B

Best Alternatives
Context / RAM
Downloads
Likes
SmollerLM2 100M Instruct Sft8K / 0.3 GB250
SmollerLM2 100M8K / 0.2 GB50
Stockmark 2 100B Instruct Beta4K / 192.9 GB5510
Saily 100b4K / 235.5 GB1837
Plankton 100M4K / 0.4 GB170
...lisLM 100M Layer Hidden Pruned2K / 0.2 GB8200
Reglu 100B2K / 2.6 GB291
Llama 161M 100B1K / 0.3 GB1623
...ephyr Smol Llama 100M DPO Full1K / 0.2 GB123
...ephyr Smol Llama 100M DPO Full1K /  GB131
Note: green Score (e.g. "73.2") means that the model is better than stockmark/stockmark-100b.

Rank the Stockmark 100B 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? 48046 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