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

Gua A V0.2 DPO Mistral 7B GGUF by thinkPy

 »  All LLMs  »  thinkPy  »  Gua A V0.2 DPO Mistral 7B GGUF   URL Share it on

  15   
  Culture   Custom code Dataset:somosnlp/dataset-cultu...   Endpoints compatible   Es   Gguf   Guaraní   Mistral   Paraguay   Q4   Quantized   Region:us   Unsloth
Model Card on HF 🤗: https://huggingface.co/thinkPy/gua-a_v0.2-dpo_mistral-7b_GGUF 

Gua A V0.2 DPO Mistral 7b GGUF Benchmarks

LLME Score: 0.18213
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gua A V0.2 DPO Mistral 7B GGUF (thinkPy/gua-a_v0.2-dpo_mistral-7b_GGUF)

Gua A V0.2 DPO Mistral 7B GGUF Parameters and Internals

Model Type 
Language model, instruction tuned
Use Cases 
Areas:
educational, cultural exploration
Primary Use Cases:
Responding to questions about Guaraní culture, Educational aid
Limitations:
Limited to the vision of the author of the book used in training, Responses may be inaccurate and of low quality
Additional Notes 
The model uses a quaternary quantization format (4-bit) stored in GGUF to improve efficiency while maintaining the quality of text generation. Suitable for resource-limited environments.
Supported Languages 
es-ES (Fluent)
Training Details 
Data Sources:
somosnlp/dataset-cultura-guarani_corpus-it
Methodology:
Direct Preference Optimization (DPO) with culturally specific data
Hardware Used:
unsloth/mistral-7b-bnb-4bit
Input Output 
Input Format:
Clear and concise questions in Spanish about the book Ñande Ypykuéra.
Accepted Modalities:
text
Output Format:
Concise responses only in Spanish.
LLM NameGua A V0.2 DPO Mistral 7b GGUF
Repository 🤗https://huggingface.co/thinkPy/gua-a_v0.2-dpo_mistral-7b_GGUF 
Model Size7b
Required VRAM4.4 GB
Updated2025-02-22
MaintainerthinkPy
Model Typemistral
Model Files  4.4 GB
Supported Languageses
GGUF QuantizationYes
Quantization Typegguf|q4|q4_k
Model ArchitectureAutoModel
Licensecc-by-sa-4.0

Best Alternatives to Gua A V0.2 DPO Mistral 7B GGUF

Best Alternatives
Context / RAM
Downloads
Likes
Pixel8K / 4.4 GB170
Mistral 7B Instruct V0.3 GGUF0K / 1.6 GB145894479
Qwen2 7B Instruct GGUF0K / 1.9 GB103427911
WizardLM 2 7B GGUF0K / 2.7 GB132146676
Conversely Mistral 7B0K / 0.2 GB2820
Deepthink Reasoning 7B GGUF0K / 4.7 GB134111
CleverBoi 7B V20K / 0.1 GB3230
Mistral 7B Instruct V0.3 GGUF0K / 2.7 GB704629
Neumind Math 7B Instruct GGUF0K / 4.7 GB2749
QwQ LCoT 7B Instruct GGUF0K / 4.7 GB1879
Note: green Score (e.g. "73.2") means that the model is better than thinkPy/gua-a_v0.2-dpo_mistral-7b_GGUF.

Rank the Gua A V0.2 DPO Mistral 7B GGUF 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? 43470 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