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

Nous Capybara 34B 6.0bpw H6 EXL2 by LoneStriker

 »  All LLMs  »  LoneStriker  »  Nous Capybara 34B 6.0bpw H6 EXL2   URL Share it on

  7   
  Autotrain compatible Dataset:ldjnr/lesswrong-amplif...   Dataset:ldjnr/pure-dove   Dataset:ldjnr/verified-camel   Endpoints compatible   Eng   Exl2   Llama   Pytorch   Quantized   Region:us   Sft   Sharded   Stablelm   Tensorflow

Nous Capybara 34B 6.0bpw H6 EXL2 Parameters and Internals

LLM NameNous Capybara 34B 6.0bpw H6 EXL2
RepositoryOpen on 🤗 
Model Size34b
Required VRAM26.5 GB
Updated2024-07-26
MaintainerLoneStriker
Model Typellama
Model Files  8.6 GB: 1-of-4   8.6 GB: 2-of-4   8.6 GB: 3-of-4   0.7 GB: 4-of-4
Supported Languagesen
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Licensemit
Context Length200000
Model Max Length200000
Transformers Version4.34.1
Tokenizer ClassYiTokenizer
Padding Token<unk>
Vocabulary Size64000
Torch Data Typebfloat16
Nous Capybara 34B 6.0bpw H6 EXL2 (LoneStriker/Nous-Capybara-34B-6.0bpw-h6-exl2)

Best Alternatives to Nous Capybara 34B 6.0bpw H6 EXL2

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Yi 34B 200K RPMerge0.2195K / 68.9 GB33554
...34B 200K Aezakmi Raw 1902 EXL20.2195K / 20.7 GB61
Yi 34B 200K MAR2024 EXL2 4bpw0.2195K / 18 GB71
Yi 34B 200K RPMerge EXL2 40bpw0.2195K / 18.1 GB4220
...mi Raw Toxic 2702 4.65bpw EXL20.2195K / 20.8 GB72
...B 200K RPMerge 4.65bpw H6 EXL20.2195K / 10.5 GB81
Opus V1 34B 5.0bpw H6 EXL20.2195K / 22.3 GB62
Opus V1 34B 4.0bpw H6 EXL20.2195K / 18 GB61
Opus V1 34B 8.0bpw H8 EXL20.2195K / 34.8 GB51
34B Beta 5.0bpw H6 EXL20.2195K / 22.3 GB61
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Nous-Capybara-34B-6.0bpw-h6-exl2.

Rank the Nous Capybara 34B 6.0bpw H6 EXL2 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? 34446 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 v2024072501
  Support LLM Explorer