seriouspark/gemma-7b-it-v0.3-lora-persona3_360

README.md

@@ -52,5 +52,5 @@ The following hyperparameters were used during training:
 - PEFT 0.8.2
 - Transformers 4.39.0
 - Pytorch 2.1.2
-- Datasets 2.17.0
+- Datasets 2.19.2
 - Tokenizers 0.15.2

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-7b-it",
+  "base_model_name_or_path": null,
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -19,12 +19,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "gate_proj",
     "down_proj",
     "k_proj",
-    "gate_proj",
-    "o_proj",
-    "q_proj",
     "up_proj",
+    "o_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:006742994fb5275114d730b60aa9aa85772e1da592dc7c2f7f0368a0bcf8b58e
-size 400084608
+oid sha256:7d7fb3cb96f78b6bf279c3ff078caf4bd6fbdcdaa0ad3b4b030d8ba0ce8edb74
+size 400104600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fab8376e19cee8dd432f485eaa9f3f0a8df8bb2de18c1d9b6ef5ab7c85e6e47
-size 4920
+oid sha256:c5e18dd421112bed671fb07745e80f2721b67f3a2fcf4fdf49c1a938140902da
+size 4856