Uploading model files

README.md

@@ -56,7 +56,7 @@ The following hyperparameters were used during training:
 ### Framework versions
 
 - PEFT 0.12.0
-- Transformers 4.48.3
+- Transformers 4.49.0
 - Pytorch 2.6.0+cu124
-- Datasets 3.2.0
+- Datasets 3.3.2
 - Tokenizers 0.21.0

adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 48,
+  "lora_alpha": 32,
   "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 24,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "qkv_proj",
+    "o_proj",
     "gate_up_proj",
-    "o_proj"
+    "down_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef81b5fd35e8fa65f6c104f563b04a81a66bee78b8f4f5d3635a09575f107937
-size 151029568
+oid sha256:68f8d6ebccf3220c90689c03acfa0915d96b14548b62ea8bd3146594e3d7c694
+size 201361312

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a7c28a90d6b46d7c068c07369ea154dc1d13db97a14954cd7f10dec5201e4df
+oid sha256:7de57386acaa5ac0a9da5a632fdf41f5bf130926e7bf5f9a032c8d2261dbc8f7
 size 5688