ClaudioSavelli/FAME_gold_llama32-1b-2p5-instruct-qa
ClaudioSavelli/FAME_gold_llama32-1b-2p5-instruct-qa is a 1 billion parameter instruction-tuned language model, a retrained (Gold) version of the Llama-3.2-1b-Instruct architecture. Developed by ClaudioSavelli, this model is specifically adapted for the FAME setting, as detailed in its associated research paper. It features a 32768 token context length, making it suitable for question-answering tasks within its specialized domain.
Loading preview...
Model Overview
ClaudioSavelli/FAME_gold_llama32-1b-2p5-instruct-qa is a 1 billion parameter instruction-tuned language model, derived from the meta-llama/Llama-3.2-1b-Instruct base model. This particular version is a "Gold" retrained iteration, specifically optimized for the FAME (Forecasting and Anomaly detection in Manufacturing Environments) setting.
Key Characteristics
- Base Model: Built upon the
meta-llama/Llama-3.2-1b-Instructarchitecture. - Parameter Count: 1 billion parameters, offering a balance between performance and computational efficiency.
- Context Length: Supports a substantial context window of 32768 tokens, enabling processing of longer inputs.
- Specialization: Retrained and optimized for the FAME setting, indicating a focus on tasks related to forecasting and anomaly detection, likely within manufacturing or similar industrial contexts.
Intended Use Cases
This model is primarily designed for:
- Question Answering (QA): Instruction-tuned for QA tasks, particularly within the FAME domain.
- FAME Setting Applications: Ideal for applications requiring language understanding and generation in the context of forecasting and anomaly detection, as outlined in the associated research paper https://arxiv.org/pdf/2512.15235.