phi-2-ele

README.md

@@ -54,5 +54,5 @@ The following hyperparameters were used during training:
 - PEFT 0.11.1
 - Transformers 4.42.3
 - Pytorch 2.1.2
-- Datasets 2.19.2
+- Datasets 2.20.0
 - Tokenizers 0.19.1

adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "fc2",
     "v_proj",
-    "q_proj",
     "dense",
-    "fc1"
+    "q_proj",
+    "fc1",
+    "k_proj",
+    "fc2"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7fd06be9ae6ee770bd7640d4d51e73cb52918fe0aba8663927b3705b849f06e
+oid sha256:5218734d6ce8b761c6beac196e59219180eddbee0ae753361cd3a53a0df652b0
 size 94422368

tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 50,
+    "max_length": 2048,
     "strategy": "LongestFirst",
     "stride": 0
   },

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9cac9f770b889c449076915c1123b6d6ea2b7a9f8f19eaffa02b76c31692e46
+oid sha256:478f84817af86eece2b95080e23f9df0db02cd4bd004fbdf29dcf98ef12226e4
 size 5368