Upload LoRA adapter (README written by author)

README.md

@@ -36,7 +36,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
 - Max sequence length: 512
 - Epochs: 1
 - Learning rate: 1e-06
-- LoRA: r=8, alpha=8
+- LoRA: r=16, alpha=16
 
 ## Usage
 

adapter_config.json

@@ -20,7 +20,7 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 8,
+  "lora_alpha": 16,
   "lora_bias": false,
   "lora_dropout": 0.0,
   "megatron_config": null,
@@ -29,17 +29,17 @@
   "peft_type": "LORA",
   "peft_version": "0.18.1",
   "qalora_group_size": 16,
-  "r": 8,
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "gate_proj",
-    "q_proj",
-    "k_proj",
     "v_proj",
+    "o_proj",
+    "down_proj",
     "up_proj",
-    "o_proj"
+    "q_proj",
+    "gate_proj",
+    "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 sha256:0273e544ada8c105aa40f52df95dfd857aed968e3c2497d9c4bc07e28d710da0
-size 66126768
+oid sha256:2a7d38eeba6e76aff8872c9173251e297ead7051cd84e2a3e087826bc8e3cc57
+size 132187888