philipp-zettl/DiffuBERTa

README.md

@@ -1,9 +1,9 @@
 ---
 library_name: peft
-license: mit
-base_model: roberta-base
+license: apache-2.0
+base_model: answerdotai/ModernBERT-base
 tags:
-- base_model:adapter:roberta-base
+- base_model:adapter:answerdotai/ModernBERT-base
 - lora
 - transformers
 model-index:
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # json_diff_model
 
-This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+This model is a fine-tuned version of [answerdotai/ModernBERT-base](https://huggingface.co/answerdotai/ModernBERT-base) on an unknown dataset.
 
 ## Model description
 

adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "roberta-base",
+  "base_model_name_or_path": "answerdotai/ModernBERT-base",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -25,12 +25,14 @@
   "peft_type": "LORA",
   "peft_version": "0.18.0",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "value",
-    "query"
+    "W2",
+    "W1",
+    "Wo",
+    "Wqkv"
   ],
   "target_parameters": null,
   "task_type": "FEATURE_EXTRACTION",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:009f0ebc48b161b2fe7208d11e03f50a578c4d35630d3d3c402b9174a1b849de
-size 1186472
+oid sha256:8d6c448070fed9614f2667f577947c4fcf2568ab8415be374da4098f3795e643
+size 9207688

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bed511479d3af073d7d61445d33928fd3952c85df7249db6f191e8627bcc318f
+oid sha256:1a12a895abe7bbcb05bb592090703378e0214bed6e79f1d64bda1d5d26998c18
 size 5777