codelion
/

gemma-3-1b-it-reasoning-grpo-lora

Text Generation

chain-of-thought

preference-learning

self-improvement

Model card Files Files and versions

codelion commited on Jul 18

Commit

0ebb621

·

verified ·

1 Parent(s): 4c1cc67

Upload model

Files changed (2) hide show

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

adapter_config.json CHANGED Viewed

@@ -25,12 +25,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
-    "down_proj",
     "o_proj",
-    "up_proj",
     "gate_proj",
     "k_proj"
   ],
   "task_type": "CAUSAL_LM",

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

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5775d228032c010601478512dbd886de391dec66c2d15967df7972d539ff2486
 size 208780928

 version https://git-lfs.github.com/spec/v1
+oid sha256:86801e11fab0344e9878e52530047a12cf9ae1deff359d774d4afe25300bd5b2
 size 208780928