GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
AL-GR
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
AL-GR
Model Tree
Qwen/Qwen2.5-0.5B
Input Modalities
Output Modalities
Supported Functionality
| Model | HR@20 | HR@100 | HR@500 | HR@1000 |
|---|---|---|---|---|
| Forge-Qwen 2.5-0.5B-Base-s1 | 0.0506 | 0.1277 | 0.2602 | 0.3068 |
| Forge-T5-Base-s1 | 0.0284 | 0.0689 | 0.1372 | 0.1557 |
Note: HR@K denotes Hit Rate at K — the proportion of test queries for which the correct answer appears in the top-K retrieved/generated results.
You can download this model locally using the huggingface_hub library:
python
import osos.environ["HF_ENDPOINT"] = "https://hf-mirror.com" # Optional: use mirror for faster download in some regionsos.environ["KMP_DUPLICATE_LIB_OK"] = "True"from huggingface_hub import snapshot_downloadsnapshot_download(repo_id='AL-GR/Forge-Qwen2.5-0.5B-s1',local_dir='{YOUR_LOCAL_DIR}', # Replace with your desired local pathlocal_dir_use_symlinks=False,)
For more details about the training setup, dataset, or evaluation protocol, please refer to the FORGE framework repository.
bibtex
@article{fu2025forge,title={FORGE: Forming Semantic Identifiers for Generative Retrieval in Industrial Datasets},author={Fu, Kairui and Zhang, Tao and Xiao, Shuwen and Wang, Ziyang and Zhang, Xinming and Zhang, Chenchi and Yan, Yuliang and Zheng, Junjun and others},journal={arXiv preprint arXiv:2509.20904},year={2025}}