LLM EXPLORER 59,420 MODELS INDEXED

Aira 2 Portuguese 1B7 by nicholasKluge

By nicholasKluge · 15 downloads

Aira 2 Portuguese 1B7 is an open-source language model by nicholasKluge. Features: 1.7b LLM, License: bigscience-bloom-rail-1.0, Instruction-Based, LLM Explorer Score: 0.07.

  Alignment   Assistant Base model:bigscience/bloom-1b... Base model:finetune:bigscience...   Bloom   Co2 eq emissions   Conversation Dataset:nicholaskluge/instruct...   Endpoints compatible   Instruct   Pt   Pytorch   Region:us   Safetensors

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 πŸ€—https://huggingface.co/nicholasKluge/Aira-2-portuguese-1B7 
Base Model(s)  Bloom 1b7   bigscience/bloom-1b7
Model Size1.7b
Required VRAM0 GB
Updated2026-08-02
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