shawhin/gemma-3-1b-tool-use

README.md

@@ -4,8 +4,8 @@ library_name: transformers
 model_name: gemma-3-1b-tool-use
 tags:
 - generated_from_trainer
-- trl
 - sft
+- trl
 licence: license
 ---
 
@@ -35,8 +35,8 @@ This model was trained with SFT.
 ### Framework versions
 
 - TRL: 0.19.1
-- Transformers: 4.53.1
-- Pytorch: 2.7.1
+- Transformers: 4.53.2
+- Pytorch: 2.6.0+cu124
 - Datasets: 4.0.0
 - Tokenizers: 0.21.2
 

adapter_config.json

@@ -13,9 +13,9 @@
   "layers_pattern": null,
   "layers_to_transform": null,
   "loftq_config": {},
-  "lora_alpha": 16,
+  "lora_alpha": 64,
   "lora_bias": false,
-  "lora_dropout": 0.1,
+  "lora_dropout": 0.05,
   "megatron_config": null,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
@@ -25,8 +25,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "k_proj",
+    "v_proj",
     "q_proj"
   ],
   "task_type": "CAUSAL_LM",

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2968fd76eeee8a9be1f2bc2c148a16aa5007b941be960e2f0242e45bff90f9d
+oid sha256:3794b465e918005e8ba83fcbc43465970d616db894677c38a3fbaf0f2f8b2992
 size 4173784

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

runs/Jul17_22-16-29_5b17db383321/events.out.tfevents.1752790594.5b17db383321.3458.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b042cf66fec3396bd189c9f3643c14a5ce653284a294cabf4a925ea78dfcfd9
+size 6887

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e29d3046e90c852986bd42bf21587b8291e74dd9f7cd0e7331787ef7877f385d
-size 6161
+oid sha256:ac139ed071484ebdc698444cba2a6854f61bb7577241b0f7fb29facaa3244dc2
+size 5752