Upload 8 files
Browse files- README.md +3 -3
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 3 |
datasets:
|
| 4 |
-
- u-10bei/
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
license: apache-2.0
|
|
@@ -33,7 +33,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
|
|
| 33 |
|
| 34 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
-
- Max sequence length:
|
| 37 |
- Epochs: 1
|
| 38 |
- Learning rate: 2e-05
|
| 39 |
- LoRA: r=64, alpha=128
|
|
@@ -59,7 +59,7 @@ model = PeftModel.from_pretrained(model, adapter)
|
|
| 59 |
|
| 60 |
## Sources & Terms (IMPORTANT)
|
| 61 |
|
| 62 |
-
Training data: u-10bei/
|
| 63 |
|
| 64 |
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
|
| 65 |
Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 3 |
datasets:
|
| 4 |
+
- u-10bei/structured_data_with_cot_dataset_v2
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
license: apache-2.0
|
|
|
|
| 33 |
|
| 34 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
+
- Max sequence length: 2048
|
| 37 |
- Epochs: 1
|
| 38 |
- Learning rate: 2e-05
|
| 39 |
- LoRA: r=64, alpha=128
|
|
|
|
| 59 |
|
| 60 |
## Sources & Terms (IMPORTANT)
|
| 61 |
|
| 62 |
+
Training data: u-10bei/structured_data_with_cot_dataset_v2
|
| 63 |
|
| 64 |
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
|
| 65 |
Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 528550256
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b68b1ed7d49ee72918b3e3f9360418f435a20ffa02e62a5768043746055cc171
|
| 3 |
size 528550256
|