Instructions to use YirongSun/glap_ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use YirongSun/glap_ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="YirongSun/glap_ft", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("YirongSun/glap_ft", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Move legacy checkpoints into old directory
Verified signatureServer-side atomic copy and root-path deletion for the three legacy .pt checkpoints. HF-native model files are unchanged.2dc39ec -
Fix tokenizer resolution for pinned offline loads
Verified signatureCorrective release for repo-id loading with revision, custom cache_dir, and offline mode. Source commit: cbf5599c5adc95c4d9f4128a0e9c6773aa2bc0d4 Model weights are unchanged.c0bc7c1 -
Publish HF-native SPEAR-GLAP best checkpoint
Verified signatureSource commit: 51eb67f67ae6a9a8aafc4b52d5e72bc7f08762e2 Best epoch: 4 Protocol: test-tuned paired text-to-audio retrieval Existing legacy .pt files are intentionally preserved.bc7147a
-
Upload Phase 2 best SPEAR-GLAP checkpoint
Verified signature7b275fb
-
Upload Phase 1 best SPEAR-GLAP checkpoint
Verified signature47396c8
-
Upload glap_spear_50k_best.pt
Verified signature47573d2 -
initial commit
Verified signaturedaded4d