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

Mistral Portuguese Luana 7B Chat by rhaymison

 »  All LLMs  »  rhaymison  »  Mistral Portuguese Luana 7B Chat   URL Share it on

  32   
  7b   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   Chat   Conversational Dataset:rhaymison/ultrachat-ea...   Endpoints compatible   Instruct   Misral   Mistral   Model-index   Portugues   Portuguese   Pt   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/rhaymison/Mistral-portuguese-luana-7b-chat 

Mistral Portuguese Luana 7B Chat Benchmarks

ARC: 59.3 vs 96.7 (so35)-38.7%
HellaSwag: 81.4 vs 95.3 (gpt4)-14.6%
MMLU: 60.84 vs 88.3 (so35)-31.1%
TruthfulQA: 54.6 vs 59 (gpt4)-7.5%
WinoGrande: 76.24 vs 87.5 (gpt4)-12.9%
GSM8K: 38.21 vs 96.4 (so35)-60.4%
LLME Score: 0.19682
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mistral Portuguese Luana 7B Chat (rhaymison/Mistral-portuguese-luana-7b-chat)

Mistral Portuguese Luana 7B Chat Parameters and Internals

Model Type 
text-generation, chat
Use Cases 
Areas:
chat, Portuguese-specific applications
Applications:
chatbots, customer service, social media interactions
Primary Use Cases:
providing chat responses in Portuguese
Additional Notes 
The model is finely tuned to fill the gap in Portuguese language models, primarily focused on chat functionalities.
Supported Languages 
Portuguese (High)
Training Details 
Data Sources:
rhaymison/ultrachat-easy-use
Data Volume:
250,000 chat examples
Methodology:
Fine-tuned for chat operations from Mistral 7b
Hardware Used:
A100, T4, V100, L4
Input Output 
Accepted Modalities:
text
Performance Tips:
Use verbs in prompts to help guide model responses. Ensure that the model is efficiently deployed in terms of computing resources to prevent memory issues like CUDA OOM errors.
LLM NameMistral Portuguese Luana 7B Chat
Repository 🤗https://huggingface.co/rhaymison/Mistral-portuguese-luana-7b-chat 
Base Model(s)  mistralai/Mistral-7B-Instruct-v0.2   mistralai/Mistral-7B-Instruct-v0.2
Model Size7b
Required VRAM14.4 GB
Updated2025-02-22
Maintainerrhaymison
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagespt
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Mistral Portuguese Luana 7B Chat

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB462011
SpydazWeb AI HumanAI RP512K / 14.4 GB121
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB120
...1 Summarize 64K LoRANET Merged128K / 14.4 GB110
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB1916301573
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB37505
...ty Instruct 3M 0625 Mistral 7B32K / 14.4 GB37063
Note: green Score (e.g. "73.2") means that the model is better than rhaymison/Mistral-portuguese-luana-7b-chat.

Rank the Mistral Portuguese Luana 7B Chat 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