phi-3-mini-QLoRA

README.md

@@ -34,8 +34,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.12.0
-- Transformers: 4.46.1
-- Pytorch: 2.5.1
+- Transformers: 4.47.0.dev0
+- Pytorch: 2.6.0.dev20241031+cu121
 - Datasets: 3.1.0
 - Tokenizers: 0.20.1
 

adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "gate_proj",
+    "down_proj",
     "k_proj",
     "up_proj",
-    "v_proj",
-    "q_proj",
     "o_proj",
-    "down_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 sha256:5980492d7515b3f8b2ddf23effe065ef0603b929e70232a3d80cf5e2937d208e
+oid sha256:4857948b5f9544edc16884106ac75ce7aa14f2a31298d848b202fbad9cc3532e
 size 35668592

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:366522af54da8b366709580193d5609018d277afe49ff393876a86bef2b0f5ab
-size 5496
+oid sha256:95e5ccd9bcf2d869ee3a4da1ed7db4ba7240997c954cc6fb579e5e5201536efd
+size 5560