cyumizou
/

llm-jp-3-13b-finetune-adapter_lora-dpo

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

cyumizou commited on 9 days ago

Commit

dbfc06d

•

1 Parent(s): 54409a8

Trained with Unsloth

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +3 -3
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "gate_proj",
     "up_proj",
-    "k_proj",
     "q_proj",
-    "v_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "v_proj",
+    "k_proj",
     "gate_proj",
+    "down_proj",
     "up_proj",
     "q_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253c1676f968458997bc681d5211f21fb30c39594f554a6e876d7f060565a9b1
 size 250422888

 version https://git-lfs.github.com/spec/v1
+oid sha256:9460444e7335f90502efa7bb4980bfb41d4adb3156d3b436974c7573d1f5d24e
 size 250422888