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

README.md

@@ -34,10 +34,10 @@ This model was trained with SFT.
 
 ### Framework versions
 
-- TRL: 0.16.0
-- Transformers: 4.50.1
+- TRL: 0.17.0
+- Transformers: 4.51.3
 - Pytorch: 2.6.0+cu124
-- Datasets: 3.4.1
+- Datasets: 3.6.0
 - Tokenizers: 0.21.1
 
 ## Citations
@@ -49,7 +49,7 @@ Cite TRL as:
 ```bibtex
 @misc{vonwerra2022trl,
 	title        = {{TRL: Transformer Reinforcement Learning}},
-	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
 	year         = 2020,
 	journal      = {GitHub repository},
 	publisher    = {GitHub},

adapter_config.json

@@ -24,15 +24,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "o_proj",
+    "embed_tokens",
+    "down_proj",
     "lm_head",
+    "gate_proj",
     "q_proj",
     "up_proj",
-    "v_proj",
-    "embed_tokens",
-    "gate_proj",
-    "o_proj",
-    "down_proj",
-    "k_proj"
+    "v_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:e187f5cc6bd7bbe6109db89bab83599b4445213bcfc853f76fd4cd2244064131
+oid sha256:f5566bbb2855ca6935130a63d1ec7fc6804307891084ae08050201fb19a7d2fb
 size 1293936232

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04bc29295560b97912b7adb4cf1f939d52985bfe392feda937699f9f3e878f6f
-size 5624
+oid sha256:08cfde619b67b4ed75a2fabf6a957f8c566fbaa6d42993c00ee1c1094e2d5c08
+size 5688