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

ae97dda

·

verified ·

1 Parent(s): 16849da

Upload model

Files changed (2) hide show

adapter_config.json +4 -4
adapter_model.safetensors +1 -1

adapter_config.json CHANGED Viewed

@@ -26,12 +26,12 @@
   "revision": null,
   "target_modules": [
     "q_proj",
-    "gate_proj",
     "down_proj",
-    "up_proj",
     "o_proj",
-    "k_proj",
-    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

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

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def8f59a32f07a7580cb045035a233b7fb63fda7fcd31115aefbeee41da54c79
 size 208780928

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