anukum/gemma3-1b-thinking

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "google/gemma-3-1b-it",
+  "base_model_name_or_path": "unsloth/gemma-3-1b-it-unsloth-bnb-4bit",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
@@ -15,24 +15,16 @@
   "loftq_config": {},
   "lora_alpha": 32,
   "lora_bias": false,
-  "lora_dropout": 0.0,
+  "lora_dropout": 0,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
-  "r": 16,
+  "r": 24,
   "rank_pattern": {},
   "revision": null,
-  "target_modules": [
-    "gate_proj",
-    "up_proj",
-    "v_proj",
-    "down_proj",
-    "o_proj",
-    "k_proj",
-    "q_proj"
-  ],
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense).*?(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj).*?)|(?:\\bmodel\\.layers\\.[\\d]{1,}\\.(?:self_attn|attention|attn|mlp|feed_forward|ffn|dense)\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19de6e1034c361e052daf63b56504fa0eaa9aa57b4a9da6464326774cdda384e
-size 52231312
+oid sha256:5bda1dce64cc4f49708338c18c38ed05e2b0221ca871213d9d61319091bbb369
+size 78322880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e80c08371c54cbef2ab609c28a29a3665a99d57afb8ca82017fc5c01e4538e5e
+oid sha256:f1d880df9b3da63cece8120117941b78bea4ea519aeaea6575c589c45192a458
 size 6264