AF0815 commited on
Commit
1c78eb7
·
verified ·
1 Parent(s): 03ff6d6

Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)

Browse files
README.md CHANGED
@@ -67,7 +67,7 @@ DB category weights used during training-data preparation:
67
  - Max sequence length: 4096
68
  - Epochs: 1
69
  - Learning rate: 2e-04
70
- - LoRA: r=32, alpha=64, dropout=0.05
71
  - Per-device train batch size: 2
72
  - Gradient accumulation: 4
73
 
 
67
  - Max sequence length: 4096
68
  - Epochs: 1
69
  - Learning rate: 2e-04
70
+ - LoRA: r=32, alpha=64, dropout=0.0
71
  - Per-device train batch size: 2
72
  - Gradient accumulation: 4
73
 
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b4f9428ff718d9cb13a3c2edc84fc40c13618001bd765b1ddb70cd26dc7b465
3
  size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f24a60ba30323e3d5891e605da2e666fd3e36119108e6910e58bec32d2233203
3
  size 4967215360
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f556fb2a665d7393d46117557f24b9ce0ff12b3f0577e160b9de892b3f11973
3
  size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:808b0a11c023548819c31b9428240fd594dae55e316e4918f0267e0dbddb65e8
3
  size 3077766632