Update README.md

Remove pytorch_model.bin (using safetensors only)

Update README: self-contained usage with trust_remote_code

Fix embed_mask for texts without separator (use entire text, not empty)

Fix model structure to match checkpoint (wrap LlamaBiModel in self.model)

Remove problematic AutoModel.register() call

Add vendored pooling_latent.py module

Update modeling_llm2vec4cxr.py with helper methods and vendored pooling

Update README.md

Update README.md

Update README.md

Create llm2vec_wrapper.py

Update config to use custom model class

Add custom model class with proper latent attention architecture

Update README.md

Update README.md

Update README.md

Upload LLM2Vec4CXR fine-tuned model

Update model with corrected safetensors metadata and proper latent attention loading

Upload model.safetensors

Delete model.safetensors

Upload LLM2Vec4CXR fine-tuned model

Upload LLM2Vec4CXR fine-tuned model

Upload LLM2Vec4CXR fine-tuned model

Upload LLM2Vec4CXR fine-tuned model

upload tokenizer

init commit

initial commit