cyumizou
/

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

text-generation-inference

Inference Endpoints

Model card Files Files and versions Community

cyumizou commited on 18 days ago

Commit

18ed890

•

1 Parent(s): 886aa85

Trained with Unsloth

Upload model trained with Unsloth 2x faster

Files changed (2) hide show

adapter_config.json +4 -4
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -16,15 +16,15 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 8,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
-    "q_proj",
     "gate_proj",
     "v_proj",
     "k_proj",
     "down_proj"
   ],

   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "q_proj",
     "v_proj",
+    "up_proj",
+    "o_proj",
     "k_proj",
     "down_proj"
   ],

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91ccd60cd38bcf2bcff0513fe3b0f06459f64c3f3c858e8bd27f2601ba8c37d8
-size 125248064

 version https://git-lfs.github.com/spec/v1
+oid sha256:36540d6056867975c388eff65600e3851c9d86b5d204531f81f018280044baed
+size 250422888