Model save

README.md

@@ -50,14 +50,10 @@ The following hyperparameters were used during training:
 - training_steps: 1
 - mixed_precision_training: Native AMP
 
-### Training results
-
-
-
 ### Framework versions
 
 - PEFT 0.10.0
-- Transformers 4.39.3
+- Transformers 4.40.0
 - Pytorch 2.2.1+cu121
 - Datasets 2.18.0
-- Tokenizers 0.15.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -20,14 +20,14 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "o_proj",
     "down_proj",
+    "lm_head",
     "up_proj",
-    "q_proj",
+    "k_proj",
+    "v_proj",
     "gate_proj",
-    "lm_head",
-    "k_proj"
+    "o_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:e7283944375ea0e7456bd0fa63d36ac0310589aa7b3a5af2bffcf155dee4ddca
+oid sha256:5735ee519c52fca43a96f79b57999e666e06a52e095c9283ac271a372dba24e6
 size 1204711776

tokenizer.json

@@ -157,6 +157,7 @@
     "end_of_word_suffix": null,
     "fuse_unk": true,
     "byte_fallback": true,
+    "ignore_merges": false,
     "vocab": {
       "<unk>": 0,
       "<s>": 1,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63bec4085a3ab4f0508fa8c2c71f8ac8c7949872150a77334880cd41368a77f5
-size 5048
+oid sha256:d124e6e5f2c5576368627386267fcd766bfb65c13c2686a9bf5ac018ea11fcb7
+size 5112