up

README.md

@@ -2,6 +2,32 @@
 license: mit
 ---
 
+# GraphJudger
 
-This is the LoRA checkpoints for the paper [Can LLMs be Good Graph Judger for Knowledge Graph Construction?](https://arxiv.org/abs/2411.17388).
+This is the LoRA weights for the paper [Can LLMs be Good Graph Judger for Knowledge Graph Construction?](https://arxiv.org/abs/2411.17388).
 
+## Example
+
+Loading:
+
+```python
+BASE_MODEL = "models/llama-2-7b-hf"
+LORA_WEIGHTS = "models/llama2-7b-lora-genwiki/"
+
+model = LlamaForCausalLM.from_pretrained(
+            BASE_MODEL,
+            load_in_8bit=False
+        ).half().cuda()
+pipeline = transformers.pipeline (
+            "text-generation",
+            model=model,
+            tokenizer=tokenizer,
+            torch_dtype=torch.float16,
+            device=device
+            )
+pipeline.model = PeftModel.from_pretrained(
+            model,
+            LORA_WEIGHTS,
+            torch_dtype=torch.float16,
+        ).half().cuda()
+```