lmassaron/gemma-3-1B-it-function_calling

README.md

@@ -35,7 +35,7 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.16.0
-- Transformers: 4.50.0
+- Transformers: 4.50.1
 - Pytorch: 2.6.0+cu124
 - Datasets: 3.4.1
 - Tokenizers: 0.21.1

adapter_config.json

@@ -24,15 +24,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
-    "k_proj",
-    "down_proj",
+    "lm_head",
     "q_proj",
     "up_proj",
+    "v_proj",
+    "embed_tokens",
+    "gate_proj",
     "o_proj",
-    "lm_head",
-    "embed_tokens"
+    "down_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8a4e0d9cf802a8bd5e3b62f7c09a2f94e15aab7c15795e09b0bc8eb92c0210
+oid sha256:e187f5cc6bd7bbe6109db89bab83599b4445213bcfc853f76fd4cd2244064131
 size 1293936232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c57f3eb27d2d3c2de68b3bb7cde743d53c2e31be8c8a05f4c6ce4cdde33003d1
+oid sha256:04bc29295560b97912b7adb4cf1f939d52985bfe392feda937699f9f3e878f6f
 size 5624