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

Cuscuz 7B by rhaymison

 »  All LLMs  »  rhaymison  »  Cuscuz 7B   URL Share it on

  12   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Conversational Dataset:rhaymison/questions an...   Endpoints compatible   Instruct   Lora   Mistral   Portuguese   Pt   Region:us   Safetensors   Sharded   Tensorflow   Version:0.1
Model Card on HF 🤗: https://huggingface.co/rhaymison/cuscuz-7b 

Cuscuz 7B Benchmarks

LLME Score: 0.13901
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cuscuz 7B (rhaymison/cuscuz-7b)
🌟 Advertise your project 🚀

Cuscuz 7B Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
specialized knowledge of the Northeast region of Brazil
Primary Use Cases:
text generation related to the Northeast region of Brazil
Additional Notes 
The model was tuned to specialize in historical, geographical, economic, cultural, and culinary issues in the Northeast region.
Supported Languages 
Portuguese (specialized in the Northeast region of Brazil)
Training Details 
Data Sources:
rhaymison/questions_answers_geo_nord
Methodology:
fine-tuning
Input Output 
Input Format:
PyTorch tensors
Accepted Modalities:
text
Output Format:
text
Performance Tips:
Use the model without quantization for better performance.
Release Notes 
Version:
0.1
Date:
09-03-2024
Notes:
Cuscuz 7b is a model derived from fine-tuning the Mixtral 7b model, specialized in the Northeast region of Brazil.
LLM NameCuscuz 7B
Repository 🤗https://huggingface.co/rhaymison/cuscuz-7b 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.1   mistralai/Mistral-7B-Instruct-v0.1
Model Size7b
Required VRAM14.4 GB
Updated2025-09-26
Maintainerrhaymison
Instruction-BasedYes
Model Files  0.1 GB   4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagespt
Model ArchitectureAutoModelForCausalLM
Licenseapache-2.0
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token</s>
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesv_proj|gate_proj|k_proj|o_proj|q_proj
LoRA Alpha16
LoRA Dropout0.05
R Param16

Best Alternatives to Cuscuz 7B

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B Instruct V0.332K / 14.5 GB395
Mistral 7B Instruct V0.332K / 14.5 GB3953
...ralai Mistral 7B Instruct V0.332K / 14.5 GB432
Mistral 7B Instruct V0.332K / 14.5 GB80
Full V4 Astromistral Final32K / 4.5 GB61
Acemath Convfinqa0K / 15.2 GB60
Monarch 10K / 14.5 GB12
Mistral 7B Instruct Uz0K / 14.5 GB11914
...phyr 7B Beta Agent Instruct V30K / 0.7 GB21
Code Llama Python0K / 0.3 GB41
Note: green Score (e.g. "73.2") means that the model is better than rhaymison/cuscuz-7b.

Rank the Cuscuz 7B 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? 51557 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