AF0815 commited on
Commit
ae921aa
·
verified ·
1 Parent(s): 53f1e30

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

Browse files
README.md CHANGED
@@ -66,7 +66,7 @@ DB category weights used during training-data preparation:
66
  - Method: LoRA (full precision base)
67
  - Max sequence length: 4096
68
  - Epochs: 1
69
- - Learning rate: 1e-04
70
  - LoRA: r=32, alpha=64, dropout=0.0
71
  - Per-device train batch size: 2
72
  - Gradient accumulation: 4
 
66
  - Method: LoRA (full precision base)
67
  - Max sequence length: 4096
68
  - Epochs: 1
69
+ - Learning rate: 8e-05
70
  - LoRA: r=32, alpha=64, dropout=0.0
71
  - Per-device train batch size: 2
72
  - Gradient accumulation: 4
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2beb942082c8119c9886cfa693a1184ac081fbba9d230758ca38b1177981cbf0
3
  size 4967215360
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d2d71802a7dcdff7594ba31701343454c03052c239272cc7ab62203b4f789df
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:c495911af49f7c7a33ca9f25eaa624ef82b2e29af78cdb18895c0ccb62ddf38f
3
  size 3077766632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d029aeebf305468eb1cdba3d8a44d06157f9e45d8918d58090276a17ae40fb1
3
  size 3077766632