amirdianov/Qwen2.5-1.5B-Instruct-abliterated-ru
This is a 1.5 billion parameter instruction-tuned causal language model, part of the Qwen2.5 family. The model is shared by amirdianov and is noted as "abliterated-ru," suggesting a focus or modification for Russian language tasks. Its primary differentiator and specific use cases are not detailed in the provided information, but its instruction-tuned nature implies general conversational and task-oriented applications.
Loading preview...
Model Overview
This model, amirdianov/Qwen2.5-1.5B-Instruct-abliterated-ru, is a 1.5 billion parameter instruction-tuned causal language model. It is part of the Qwen2.5 family, indicating a foundation in that architecture. The "abliterated-ru" in its name suggests a potential specialization or modification for the Russian language, though specific details on this are not provided in the current model card.
Key Characteristics
- Model Type: Instruction-tuned causal language model.
- Parameter Count: 1.5 billion parameters.
- Context Length: 32768 tokens.
- Language Focus: Implied focus on Russian due to "abliterated-ru" in the name.
Limitations and Recommendations
The model card explicitly states that more information is needed regarding its development, funding, specific model type, language(s), license, and finetuning origins. Consequently, details on direct use, downstream use, out-of-scope use, biases, risks, and limitations are currently unspecified. Users are advised that more information is required for further recommendations regarding its application and potential issues.