Portuguese optimization
According to the model card, the model was specially optimized to understand and respond in Portuguese.
Open Source Model Profile · botbotrobotics
CabraLlama3-8b
CabraLlama3-8b is an 8.03B-parameter Llama text-generation fine-tune from botbotrobotics. Its model card describes refinement of Meta-Llama-3-8B-Instruct on the Cabra 30k dataset for Portuguese.
- Publisher
- botbotrobotics
- Task
- text-generation
- Model type
- llama
- License
- cc-by-nc-2.0
- Library
- transformers
- Publication status
- Accepted · not indexed
Model overview
CabraLlama3-8b is published by botbotrobotics as a text-generation model. The captured configuration identifies LlamaForCausalLM with model type llama, and Safetensors metadata reports 8,030,261,248 parameters. According to the model card, it is an improved Meta-Llama-3-8B-Instruct version optimized for Portuguese.
Recorded capabilities
Named instruction base
The publisher identifies Meta-Llama-3-8B-Instruct as the base model.
Cabra 30k refinement
According to the model card, refinement used the internal Cabra 30k fine-tuning dataset.
Use cases in the source record
- Portuguese conversational text generation of the kind the publisher describes for this fine-tune.
- Dialogue work building on the publisher-named Meta-Llama-3-8B-Instruct base.
Limitations and unknowns
- No evaluation results were extracted from this record.
- No context-window value was extracted from this record.
- Dataset release status is described as forthcoming in the model card and was not independently verified.
- Provider state is historical snapshot data, not independently refreshed current availability.
Source and provenance
Source: botbotrobotics/CabraLlama3-8b
Captured: Unknown. Processed: 2026-09-07T19:34:41.837110+00:00.
Cabra Llama-3 8B O Cabra Llama-3 8B é uma versão aprimorada do Meta-Llama-3-8B-Instruct, refinado com o uso do dataset Cabra 30k. Este modelo foi especialmente otimizado para compreender e responder em português. Experimente o modelo no nosso chat . Conheça os nossos outros modelos e datasets , e o Cabra Llama 3 70b . Detalhes do modelo base Modelo: Meta-Llama-3-8B-Instruct A Meta desenvolveu e lançou a família de modelos Llama 3, uma coleção de modelos de texto generativos pré-treinados e ajustados por instruções nos tamanhos de 8B e 70B. Os modelos Llama 3 ajustados por instruções são otimizados para casos de uso em diálogos e sup…
F001F002F003F004F005F006F007F008F009F010F011F014F015