georgeliu59/retrieval_trainset_100_022726
The georgeliu59/retrieval_trainset_100_022726 model is an 8 billion parameter language model, fine-tuned from Qwen/Qwen3-VL-8B-Instruct. This model is specifically optimized for retrieval tasks, having been trained on the retrieval_trainset_100_022726 dataset. It leverages a 32768 token context length, making it suitable for applications requiring extensive context understanding in retrieval-based scenarios.
Loading preview...
Model Overview
This model, georgeliu59/retrieval_trainset_100_022726, is an 8 billion parameter language model derived from the Qwen/Qwen3-VL-8B-Instruct architecture. It has been specifically fine-tuned on the retrieval_trainset_100_022726 dataset, indicating an optimization for retrieval-oriented tasks. The model supports a substantial context length of 32768 tokens, which is beneficial for processing and understanding long documents or complex queries in retrieval applications.
Training Details
The fine-tuning process involved a learning rate of 3e-05 over 4.0 epochs, utilizing a cosine learning rate scheduler with a 0.05 warmup ratio. Training was conducted with a total_train_batch_size of 320 across 16 devices, employing adamw_torch as the optimizer.
Intended Use Cases
This model is primarily intended for use cases that involve information retrieval, where its fine-tuning on a dedicated retrieval dataset and large context window can be leveraged. Developers can consider this model for applications requiring efficient and accurate document or passage retrieval based on complex queries.