Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)
Browse files- README.md +3 -3
- model-00001-of-00002.safetensors +1 -1
- model-00002-of-00002.safetensors +1 -1
README.md
CHANGED
|
@@ -56,7 +56,7 @@ DB category weights used during training-data preparation:
|
|
| 56 |
- comparison: 2
|
| 57 |
- ranking: 1
|
| 58 |
- select: 1
|
| 59 |
-
- insert:
|
| 60 |
- update: 1
|
| 61 |
- other: 2
|
| 62 |
|
|
@@ -65,9 +65,9 @@ DB category weights used during training-data preparation:
|
|
| 65 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 66 |
- Method: LoRA (full precision base)
|
| 67 |
- Max sequence length: 2048
|
| 68 |
-
- Epochs:
|
| 69 |
- Learning rate: 3e-06
|
| 70 |
-
- LoRA: r=32, alpha=64, dropout=0.
|
| 71 |
- Per-device train batch size: 2
|
| 72 |
- Gradient accumulation: 4
|
| 73 |
|
|
|
|
| 56 |
- comparison: 2
|
| 57 |
- ranking: 1
|
| 58 |
- select: 1
|
| 59 |
+
- insert: 1
|
| 60 |
- update: 1
|
| 61 |
- other: 2
|
| 62 |
|
|
|
|
| 65 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 66 |
- Method: LoRA (full precision base)
|
| 67 |
- Max sequence length: 2048
|
| 68 |
+
- Epochs: 1.2
|
| 69 |
- Learning rate: 3e-06
|
| 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:
|
| 3 |
size 4967215360
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d86d035157638b5b61b6a697d95689dc904183a701c9a55532830262931e5f7
|
| 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:
|
| 3 |
size 3077766632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:96924722908fbf612b2cfc1bf36bf5543ce03d982cba4ca7e4d4f583619b45bf
|
| 3 |
size 3077766632
|