abcorrea/struct-v1

adapter_config.json

@@ -28,13 +28,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "up_proj",
     "q_proj",
+    "k_proj",
     "v_proj",
+    "up_proj",
+    "o_proj",
     "down_proj",
-    "k_proj",
-    "o_proj"
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:229cb76837b8ba1f34eca6ea6e6ed655b7a284444654715a91b7c09910b78301
+oid sha256:fdddf540b862327c5f9c0c059ae55d1169580dd8d194871d3b57025d42aea4c6
 size 1688012760

tokenizer_config.json

@@ -231,7 +231,7 @@
   "eos_token": "<|im_end|>",
   "errors": "replace",
   "extra_special_tokens": {},
-  "model_max_length": 32768,
+  "model_max_length": 262144,
   "pad_token": "<|endoftext|>",
   "split_special_tokens": false,
   "tokenizer_class": "Qwen2Tokenizer",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25f8e8bc16bd43a4a3a43615b651c47ec7eff104a573bd2eb2141c376324065
+oid sha256:fef92124b4eaa801581b5f0ac6ec1adeb12b35802780e0b143713d9be088386e
 size 6161