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 7B V1.9 GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Nous Capybara 7B V1.9 GPTQ   URL Share it on

  7   
  4-bit   Autotrain compatible Base model:nousresearch/nous-c... Base model:quantized:nousresea... Dataset:ldjnr/lesswrong-amplif...   Dataset:ldjnr/pure-dove   Dataset:ldjnr/verified-camel   Eng   Gptq   Mistral   Quantized   Region:us   Safetensors   Sft   Stablelm
Model Card on HF 🤗: https://huggingface.co/TheBloke/Nous-Capybara-7B-v1.9-GPTQ 

Nous Capybara 7B V1.9 GPTQ Benchmarks

LLME Score: 0.1163
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Nous Capybara 7B V1.9 GPTQ (TheBloke/Nous-Capybara-7B-v1.9-GPTQ)
🌟 Advertise your project 🚀

Nous Capybara 7B V1.9 GPTQ Parameters and Internals

Model Type 
mistral
Use Cases 
Areas:
Research Applications
Additional Notes 
The model utilizes a novel data synthesis technique called Amplify-instruct, with enhanced quality curation for training data.
Supported Languages 
eng (fluent)
Training Details 
Data Sources:
LDJnr/LessWrong-Amplify-Instruct, LDJnr/Pure-Dove, LDJnr/Verified-Camel
Data Volume:
20K examples
Methodology:
Amplify-instruct, novel unalignment techniques, multi-turn conversations
Model Architecture:
Mistral
Input Output 
Input Format:
USER: {prompt} ASSISTANT:
LLM NameNous Capybara 7B V1.9 GPTQ
Repository 🤗https://huggingface.co/TheBloke/Nous-Capybara-7B-v1.9-GPTQ 
Model NameNous Capybara 7B v1.9
Model CreatorNousResearch
Base Model(s)  NousResearch/Nous-Capybara-7B-V1.9   NousResearch/Nous-Capybara-7B-V1.9
Model Size7b
Required VRAM4.2 GB
Updated2025-09-23
MaintainerTheBloke
Model Typemistral
Model Files  4.2 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureMistralForCausalLM
Licensemit
Context Length32768
Model Max Length32768
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Nous Capybara 7B V1.9 GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...enHermes 2.5 Mistral 7B Marlin32K / 4.1 GB5842
Zephyr 7B Beta Marlin32K / 4.1 GB1050
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB522722
...ral 7B Instruct V0.3 GPTQ 4bit32K / 4.2 GB294618
...ephyr 7B Beta Channelwise Gptq32K / 4 GB64690
Mistral 7B Instruct V0.3 GPTQ32K / 4.2 GB3831
...istral 7B Pruned50 GPTQ Marlin32K / 4 GB60
Mistral 7B Unsloth Gptq 8bit32K / 7.7 GB70
Mistral 7B Instruct V0.2 GPTQ32K / 4.2 GB599854
...phyr 7B Beta Assistant V1 Gptq32K / 4.2 GB61
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Nous-Capybara-7B-v1.9-GPTQ.

Rank the Nous Capybara 7B V1.9 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? 51539 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