Upload 3 files

This commit adds the trained logistic regression (LR) probing model files used in our paper:

**"Sentinel: Attention Probing of Proxy Models for LLM Context Compression with an Understanding Perspective"**

These models perform sentence-level relevance prediction based on decoder attention features from a 0.5B-scale proxy model (Qwen2.5-0.5B-Instruct). The logistic regression classifier is trained on attention-derived features from SQuAD, NewsQA, and HotpotQA under weak supervision.

📂 Files:
- `.pkl`: Serialized LR classifier weights
- `.json`: Feature configuration used during probing

These files correspond to the setup described in Section 2.3 of the paper. Use them to replicate the results in our LongBench evaluations.

📄 Paper: https://arxiv.org/abs/2505.23277
🔗 Code: https://github.com/yzhangchuck/Sentinel

qwen2.5-0.5b-instruct-3000_all_layer_last_token_20250515_033938_model.json

@@ -0,0 +1,33 @@
+{
+  "19": [
+    6,
+    2
+  ],
+  "3": [
+    4
+  ],
+  "15": [
+    12
+  ],
+  "0": [
+    5,
+    7,
+    9
+  ],
+  "8": [
+    3
+  ],
+  "20": [
+    12
+  ],
+  "11": [
+    7
+  ],
+  "16": [
+    3,
+    7
+  ],
+  "18": [
+    13
+  ]
+}

qwen2.5-0.5b-instruct-3000_all_layer_last_token_20250515_033938_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6021b0aca86f909ebee4ec9675abd6677114ccd2140ed6ce451a40c519897ae5
+size 105439

qwen2.5-0.5b-instruct-3000_all_layer_last_token_qwen2_20250507_212739_model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73cc99327606b25a8f9752f5c80fbd7ea5be8c323b928c388591163d7626de8a
+size 107984