Aira 2 Portuguese 1B7 by nicholasKluge

 ยป  All LLMs  ยป  nicholasKluge  ยป  Aira 2 Portuguese 1B7   URL Share it on

  Alignment   Assistant   Autotrain compatible   Bloom   Co2 eq emissions   Conversation Dataset:nicholaskluge/instruct...   Endpoints compatible   Instruct   Pt   Pytorch   Region:us   Safetensors

Aira 2 Portuguese 1B7 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Aira 2 Portuguese 1B7 (nicholasKluge/Aira-2-portuguese-1B7)

Aira 2 Portuguese 1B7 Parameters and Internals

Model Type 
instruction-tuned, text generation, conversation, assistant
Use Cases 
Limitations:
Hallucinations, Biases and Toxicity, Repetition and Verbosity
Additional Notes 
This model is instruction-tuned and based on BLOOM. Three special tokens are used to mark user input and the model's response.
Supported Languages 
Portuguese (high proficiency)
Training Details 
Data Sources:
nicholasKluge/instruct-aira-dataset
Methodology:
fine-tuning
Hardware Used:
1 NVIDIA A100-SXM4-40GB
LLM NameAira 2 Portuguese 1B7
Repository ๐Ÿค—https://huggingface.co/nicholasKluge/Aira-2-portuguese-1B7 
Model Size1.7b
Required VRAM0 GB
Updated2024-12-22
MaintainernicholasKluge
Model Typebloom
Instruction-BasedYes
Model Files  6.9 GB   6.5 GB   6.9 GB   0.0 GB   0.0 GB
Supported Languagespt
Model ArchitectureBloomForCausalLM
Licensebigscience-bloom-rail-1.0
Transformers Version4.34.0
Tokenizer ClassBloomTokenizer
Padding Token<|pad|>
Vocabulary Size250684
Torch Data Typefloat32

Rank the Aira 2 Portuguese 1B7 Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 40066 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217