viamr-project/qwen3-1.7b-amr-20260705-0708
The viamr-project/qwen3-1.7b-amr-20260705-0708 is a 2 billion parameter model, likely based on the Qwen3 architecture, with a context length of 32768 tokens. This model has been evaluated on 1898 samples, achieving an average F1 score of 80.28, average precision of 80.00, and average recall of 81.07. It is designed for tasks where these specific evaluation metrics are critical, indicating a focus on balanced performance in classification or information extraction tasks.
Loading preview...
Model Overview
The viamr-project/qwen3-1.7b-amr-20260705-0708 is a 2 billion parameter language model, likely derived from the Qwen3 family, featuring a substantial context window of 32768 tokens. This model has undergone specific evaluation, demonstrating a balanced performance across key metrics.
Key Capabilities & Performance
- Evaluation Metrics: The model was evaluated on a dataset of 1898 samples.
- Average F1 Score: Achieved an average F1 score of 80.28, indicating a strong balance between precision and recall.
- Average Precision: Recorded an average precision of 80.00.
- Average Recall: Demonstrated an average recall of 81.07.
Good For
- Tasks requiring balanced performance: Its strong F1 score suggests suitability for applications where both false positives and false negatives are important to minimize.
- Specific classification or information extraction: The reported metrics are typical for models optimized for these types of tasks, especially when a high degree of accuracy and completeness is needed.
- Applications needing a large context window: The 32768-token context length allows for processing and understanding longer inputs or documents.