Upload LoRA adapter (README written by author)
Browse files- README.md +3 -4
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -1,7 +1,6 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-4B-Instruct-2507
|
| 3 |
-
|
| 4 |
-
- u-10bei/structured_data_with_cot_dataset_512_v2
|
| 5 |
language:
|
| 6 |
- en
|
| 7 |
license: apache-2.0
|
|
@@ -35,7 +34,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
|
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
- Max sequence length: 512
|
| 37 |
- Epochs: 2
|
| 38 |
-
- Learning rate:
|
| 39 |
- LoRA: r=64, alpha=128
|
| 40 |
|
| 41 |
## Usage
|
|
@@ -59,7 +58,7 @@ model = PeftModel.from_pretrained(model, adapter)
|
|
| 59 |
|
| 60 |
## Sources & Terms (IMPORTANT)
|
| 61 |
|
| 62 |
-
Training data:
|
| 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 |
+
|
|
|
|
| 4 |
language:
|
| 5 |
- en
|
| 6 |
license: apache-2.0
|
|
|
|
| 34 |
- Method: QLoRA (4-bit)
|
| 35 |
- Max sequence length: 512
|
| 36 |
- Epochs: 2
|
| 37 |
+
- Learning rate: 2.00e-05
|
| 38 |
- LoRA: r=64, alpha=128
|
| 39 |
|
| 40 |
## Usage
|
|
|
|
| 58 |
|
| 59 |
## Sources & Terms (IMPORTANT)
|
| 60 |
|
| 61 |
+
Training data: Local file: /content/drive/MyDrive/Colab Notebooks/LLMAdvanced_MainCompetition/merged_dataset_final_clean.jsonl
|
| 62 |
|
| 63 |
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
|
| 64 |
Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
|
adapter_config.json
CHANGED
|
@@ -33,13 +33,13 @@
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
|
|
|
|
|
|
|
|
|
| 36 |
"down_proj",
|
| 37 |
"k_proj",
|
| 38 |
-
"v_proj",
|
| 39 |
"gate_proj",
|
| 40 |
-
"
|
| 41 |
-
"up_proj",
|
| 42 |
-
"o_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
|
|
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
+
"q_proj",
|
| 37 |
+
"v_proj",
|
| 38 |
+
"o_proj",
|
| 39 |
"down_proj",
|
| 40 |
"k_proj",
|
|
|
|
| 41 |
"gate_proj",
|
| 42 |
+
"up_proj"
|
|
|
|
|
|
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
| 45 |
"task_type": "CAUSAL_LM",
|
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 sha256:33e4186b28b29858a0d347bc5c88fe1f4fac7474bba4dd87a5fecc5b055085f5
|
| 3 |
size 528550256
|