alibidaran
/

LLAMA3.2-Reasoning-GRPO

Model card Files Files and versions Community

alibidaran commited on Mar 7

Commit

ca8494c

·

verified ·

1 Parent(s): e1e3e90

Upload model

Files changed (2) hide show

adapter_config.json +1 -1
adapter_model.safetensors +2 -2

adapter_config.json CHANGED Viewed

@@ -22,7 +22,7 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "r": 16,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
+  "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96aef8e8e66cfb793c2458d8bd71db7114a842bc60b18f8cefaa87f0f998f394
-size 18365064

 version https://git-lfs.github.com/spec/v1
+oid sha256:059230c2dc48f29467ac7aa0a060b2289fc8563c36b0f7e23a4e9c0febe50987
+size 36715216