train_dataset_1

README.md

@@ -34,7 +34,7 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.12.1
+- TRL: 0.12.2
 - Transformers: 4.46.3
 - Pytorch: 2.5.1
 - Datasets: 3.1.0

adapter_config.json

@@ -3,6 +3,8 @@
   "auto_mapping": null,
   "base_model_name_or_path": "openchat/openchat_3.5",
   "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
   "fan_in_fan_out": false,
   "inference_mode": true,
   "init_lora_weights": true,
@@ -11,6 +13,7 @@
   "layers_to_transform": null,
   "loftq_config": {},
   "lora_alpha": 32,
+  "lora_bias": false,
   "lora_dropout": 0.1,
   "megatron_config": null,
   "megatron_core": "megatron.core",
@@ -20,13 +23,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "o_proj",
-    "up_proj",
-    "q_proj",
-    "k_proj",
     "down_proj",
-    "gate_proj"
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "v_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 sha256:0d5a7bb5e064e6221e56a7cb302279439886c17c8f80ac4861ccb41e4dd83154
+oid sha256:1e6db12f4be671d1e5286c83af8b0d8d876873a31df2bf63dac125e2ed261507
 size 167832240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca5d9f3526f9710fe2b1ba6ffac51ca0b6dd0ec865918498be755cfcbb3d7d21
+oid sha256:7b192962c59342e3727e8dd476125a52c313729a9d2e92f3ea929e9c0946c3cf
 size 5496