Uploading model files

README.md

@@ -24,7 +24,7 @@ More information needed
 
 ## Training procedure
 
-### Training hyperparameters
+
 
 ### Framework versions
 

adapter_config.json

@@ -10,20 +10,23 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
-  "lora_dropout": 0.0,
+  "lora_alpha": 32,
+  "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_up_proj",
-    "qkv_proj",
+    "down_proj",
+    "v_proj",
+    "k_proj",
     "o_proj",
-    "down_proj"
+    "up_proj",
+    "gate_proj",
+    "q_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:ed2fa81f19e37cbcaaaeae28f9d79464d780371bc06f5baef36e240040a2a2d1
-size 19778064
+oid sha256:5dc7bea71fbb2c810127319f4fdc02c8f59db905855677550cdc682c77fcf9cc
+size 239536272

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce758f201c52d51616fb39bf04ef7b1cf8ed4b16101b9b455341b9b66ea346f9
+oid sha256:1ec79086eb81daef9afa4906c9db63987a3e3576421cffdc1445ab5bd19d3ef5
 size 5752