Uploading model files

README.md

@@ -24,6 +24,8 @@ More information needed
 
 ## Training procedure
 
+### Training hyperparameters
+
 
 
 ### Framework versions

adapter_config.json

@@ -10,20 +10,20 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 64,
+  "lora_alpha": 128,
   "lora_dropout": 0.0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 32,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "o_proj",
-    "gate_up_proj",
     "qkv_proj",
-    "down_proj"
+    "gate_up_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:431876264344fa5d41877afe524fba500bc8b7c43fdeedcd5c690d89993630d4
-size 184584072
+oid sha256:6a24c24ea66c20b113a0c4477f5c3758629e0968b71f6e894a97511baed4051b
+size 369133600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf2a6ac7e95388b07ef823adc6e2c2c296f79334f70a46ae2e2e548189859d50
+oid sha256:18fb2eedb3fb9129e008364be887449984dd187e0d99076c3d4c70f1417d3f6f
 size 5752