Dobby/KOKO-Instruct

README.md

@@ -46,7 +46,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: constant
 - lr_scheduler_warmup_steps: 0.03
-- training_steps: 20
+- training_steps: 100
 
 ### Training results
 

adapter_config.json

@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj"
+    "q_proj",
+    "v_proj"
   ],
   "task_type": "CASUAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbec701c35639de2a71ae9b4eb590981b3efac049ac9a0db091941d050c5383a
+oid sha256:2a7b9568d612273c43d1e7ab32587db2f5c841c03c888191c1d2edab5dc4a323
 size 109069176

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:611f928378556ff4d39b41695fc29c664f641d709bebb7757d79e054db8450cb
+oid sha256:1a4b3c19ba04834c709a8769f5c3e0e5ac505b1085e51597e1c7d8f3db9c38bf
 size 4984