Text Retrieval
Transformers
Safetensors
English
qwen3
information-retrieval
LLM
Embedding
disaster-management
text-generation-inference
Instructions to use DMIR01/DMRetriever-596M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use DMIR01/DMRetriever-596M with Transformers:
# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("DMIR01/DMRetriever-596M") model = AutoModel.from_pretrained("DMIR01/DMRetriever-596M") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -158,7 +158,7 @@ for i, q in enumerate(queries_raw):
|
|
| 158 |
1. The **backbone** used in DMRetriever is **Bidirectional Qwen3**, not the standard Qwen3.
|
| 159 |
Please ensure that the `bidirectional_qwen3` module (included in the released model checkpoint folder) is correctly placed inside your model directory.
|
| 160 |
|
| 161 |
-
2. Make sure that your **transformers** library version is **
|
| 162 |
`KeyError: 'qwen3'`.
|
| 163 |
|
| 164 |
|
|
|
|
| 158 |
1. The **backbone** used in DMRetriever is **Bidirectional Qwen3**, not the standard Qwen3.
|
| 159 |
Please ensure that the `bidirectional_qwen3` module (included in the released model checkpoint folder) is correctly placed inside your model directory.
|
| 160 |
|
| 161 |
+
2. Make sure that your **transformers** library version is **> 4.51.0** to avoid the error:
|
| 162 |
`KeyError: 'qwen3'`.
|
| 163 |
|
| 164 |
|