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

Falcon2 5.5B Portuguese by ssmits

 »  All LLMs  »  ssmits  »  Falcon2 5.5B Portuguese   URL Share it on

  7   
  Merged Model   Autotrain compatible Base model:finetune:tiiuae/fal...   Base model:tiiuae/falcon-11b   Conversational   Custom code   Endpoints compatible   Falcon   Pt   Region:us   Safetensors   Sharded   Tensorflow   Tiiuae/falcon-11b
Model Card on HF 🤗: https://huggingface.co/ssmits/Falcon2-5.5B-Portuguese 

Falcon2 5.5B Portuguese Benchmarks

LLME Score: 0.15255
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Falcon2 5.5B Portuguese (ssmits/Falcon2-5.5B-Portuguese)
🌟 Advertise your project 🚀

Falcon2 5.5B Portuguese Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, foundation for specialization
Applications:
summarization, text generation, chatbot
Limitations:
generalization issues to unsupported languages, biases from web-corpora
Considerations:
Tailor to specific tasks and assessments.
Additional Notes 
This model was part of a merge using mergekit with specific layer configurations.
Supported Languages 
Portuguese (native), English (proficient), German (proficient), Spanish (proficient), French (proficient), Italian (proficient), Polish (proficient), Dutch (proficient), Romanian (proficient), Czech (proficient), Swedish (proficient)
Training Details 
Data Sources:
wikimedia/wikipedia Portuguese subset
Methodology:
continued pre-training and pruning using layer similarity to maintain performance while reducing model size
Safety Evaluation 
Methodologies:
PruneMe layer similarity analysis
Risk Categories:
bias, generalization issues
Responsible Ai Considerations 
Mitigation Strategies:
Fine-tuning and guardrails recommended for production use.
Input Output 
Input Format:
Text
Accepted Modalities:
text
Output Format:
Text
Performance Tips:
Use PyTorch 2.0 for optimal inference with Falcon models
Release Notes 
Notes:
Merged using passthrough method and pruned with PruneMe for optimized performance.
LLM NameFalcon2 5.5B Portuguese
Repository 🤗https://huggingface.co/ssmits/Falcon2-5.5B-Portuguese 
Base Model(s)  Falcon 11B   tiiuae/falcon-11B
Merged ModelYes
Model Size11b
Required VRAM10.9 GB
Updated2025-08-18
Maintainerssmits
Model Typefalcon
Model Files  0.9 GB: 1-of-12   1.0 GB: 2-of-12   0.9 GB: 3-of-12   0.9 GB: 4-of-12   1.0 GB: 5-of-12   0.9 GB: 6-of-12   0.9 GB: 7-of-12   1.0 GB: 8-of-12   0.9 GB: 9-of-12   0.9 GB: 10-of-12   1.0 GB: 11-of-12   0.6 GB: 12-of-12
Supported Languagespt
Model ArchitectureFalconForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.40.2
Is Biased0
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|endoftext|>
Vocabulary Size65024
Torch Data Typebfloat16

Best Alternatives to Falcon2 5.5B Portuguese

Best Alternatives
Context / RAM
Downloads
Likes
Falcon 11B8K / 22.1 GB5563215
Falcon2 5.5B Multilingual8K / 10.9 GB53
Falcon2 5.5B Polish8K / 10.9 GB24071
Falcon2 11B8K / 6.6 GB70
Enron Falcon 11B8K / 7.6 GB141
Falcon2 5.5B Italian8K / 10.9 GB210
Falcon2 5.5B Czech8K / 10.9 GB60
Falcon2 5.5B Spanish8K / 10.9 GB50
Falcon2 5.5B Norwegian8K / 10.9 GB51
Falcon2 5.5B Romanian8K / 10.9 GB41
Note: green Score (e.g. "73.2") means that the model is better than ssmits/Falcon2-5.5B-Portuguese.

Rank the Falcon2 5.5B Portuguese 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? 51558 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