Trained Model V3

adapter_config.json

@@ -13,20 +13,26 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 32,
+  "lora_alpha": 16,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 64,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "gate_proj",
+    "down_proj",
     "v_proj",
-    "q_proj"
+    "up_proj",
+    "o_proj",
+    "lm_head",
+    "k_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04733ca6d825499a3274114b6f6d3572f7b26f4114f74b69501be4d49c3c467d
-size 27280152
+oid sha256:8a5aa3e4a88cf6e38ee91fed0504480cc39c160492b478d439fcb54a879b7b41
+size 942534096