Update Readme to include peft requirement
Browse files
README.md
CHANGED
|
@@ -79,6 +79,8 @@ print(f"True probability: {true_prob:.4f}, False probability: {false_prob:.4f}")
|
|
| 79 |
|
| 80 |
This example demonstrates how to use the model to assess the relevance of an image with respect to a query. It outputs the probability that the image is relevant ("True") or not relevant ("False").
|
| 81 |
|
|
|
|
|
|
|
| 82 |
## Performance Metrics
|
| 83 |
|
| 84 |
The model has been evaluated on [ViDoRe Benchmark](https://huggingface.co/spaces/vidore/vidore-leaderboard), by retrieving 10 elements with [MrLight_dse-qwen2-2b-mrl-v1](https://huggingface.co/MrLight/dse-qwen2-2b-mrl-v1) and reranking them. The table below summarizes its `ndcg@5` scores:
|
|
|
|
| 79 |
|
| 80 |
This example demonstrates how to use the model to assess the relevance of an image with respect to a query. It outputs the probability that the image is relevant ("True") or not relevant ("False").
|
| 81 |
|
| 82 |
+
**Note**: this example requires `peft` to be installed in your environment (`pip install peft`). If you don't want to use `peft`, you can use model.[load_adapter](https://huggingface.co/docs/transformers/peft#transformers.integrations.PeftAdapterMixin.load_adapter) on the original Qwen2-VL-2B model.
|
| 83 |
+
|
| 84 |
## Performance Metrics
|
| 85 |
|
| 86 |
The model has been evaluated on [ViDoRe Benchmark](https://huggingface.co/spaces/vidore/vidore-leaderboard), by retrieving 10 elements with [MrLight_dse-qwen2-2b-mrl-v1](https://huggingface.co/MrLight/dse-qwen2-2b-mrl-v1) and reranking them. The table below summarizes its `ndcg@5` scores:
|