cyumizou
/

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

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

cyumizou commited on 20 days ago

Commit

113d80c

•

1 Parent(s): 0a46898

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": [
     "gate_proj",
     "o_proj",
-    "q_proj",
-    "k_proj",
     "v_proj",
-    "down_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

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

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d824e8eebcf4c7e2539e84b0d7b499a4890b11f8c641f448e0bb98857a834726
 size 125248064

 version https://git-lfs.github.com/spec/v1
+oid sha256:aeda9b7993d673c1b4757c48f422afdceb0078a63553b4e87470578a79dd6459
 size 125248064