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

Nucleus 22B Token 500B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Nucleus 22B Token 500B GPTQ   URL Share it on

  22   
  4-bit   Autotrain compatible Base model:nucleusai/nucleus-2... Base model:quantized:nucleusai...   En   Gptq   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/nucleus-22B-token-500B-GPTQ 

Nucleus 22B Token 500B GPTQ Benchmarks

LLME Score: 0.14701
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nucleus 22B Token 500B GPTQ (TheBloke/nucleus-22B-token-500B-GPTQ)

Nucleus 22B Token 500B GPTQ Parameters and Internals

Model Type 
causal decoder-only
Use Cases 
Areas:
Research
Applications:
Large language models, Summarization, Text generation, Chatbots
Primary Use Cases:
Foundation for further specialization and finetuning
Limitations:
Not suitable for production use without adequate assessment of risks
Considerations:
Bias and stereotypical content may exist.
Additional Notes 
The model performs well compared to similar-sized open-source models owing to its training on a large corpus.
Supported Languages 
English (primary)
Training Details 
Data Sources:
RefinedWeb-English, Books, Code, Technical, Math
Data Volume:
500B tokens
Context Length:
2048
Training Time:
two weeks in early August 2023
Hardware Used:
256 A100 80GB GPUs
Model Architecture:
similar to Llama [7B]
Responsible Ai Considerations 
Fairness:
The model may carry stereotypes and biases from the web.
Mitigation Strategies:
Finetuning for specific tasks and implementing guardrails for production use are recommended.
LLM NameNucleus 22B Token 500B GPTQ
Repository 🤗https://huggingface.co/TheBloke/nucleus-22B-token-500B-GPTQ 
Model NameNucleus 22B Token 500B
Model CreatorNucleusAI
Base Model(s)  Nucleus 22B Token 500B   NucleusAI/nucleus-22B-token-500B
Model Size22b
Required VRAM11.6 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  11.6 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Nucleus 22B Token 500B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Llama2 22B Daydreamer V3 GPT4K / 12 GB60
Llama2 22B Daydreamer V3 GPTQ4K / 12 GB227
Llama2 22B Daydreamer V2 GPTQ4K / 12 GB138
Ypotryll 22B Gptq4K / 12 GB41
Llama2 22B GPLATTY GPT4K / 12 GB60
Huginn 22B Prototype GPTQ4K / 12 GB271
Llama2 22B GPLATTY GPTQ4K / 12 GB195
Dendrite 22Bchk2 F164K / 43.7 GB101
Calm3 22B Chat16K / 44.9 GB549872
Calm3 22B RP V216K / 44.9 GB13911
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/nucleus-22B-token-500B-GPTQ.

Rank the Nucleus 22B Token 500B GPTQ 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? 42625 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