Upload LoRA adapter (Fixed README metadata)
Browse files- README.md +4 -4
- adapter_config.json +5 -5
- adapter_model.safetensors +2 -2
- all_experiments_details.json +0 -0
README.md
CHANGED
|
@@ -38,9 +38,9 @@ while intermediate reasoning (Chain-of-Thought) is masked.
|
|
| 38 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 39 |
- Method: QLoRA (4-bit)
|
| 40 |
- Max sequence length: 512
|
| 41 |
-
- Epochs:
|
| 42 |
-
- Learning rate: 1e-
|
| 43 |
-
- LoRA: r=
|
| 44 |
|
| 45 |
## Usage
|
| 46 |
|
|
@@ -63,7 +63,7 @@ model = PeftModel.from_pretrained(model, adapter)
|
|
| 63 |
|
| 64 |
## Sources & Terms (IMPORTANT)
|
| 65 |
|
| 66 |
-
Training data: ['u-10bei/structured_data_with_cot_dataset_512', 'u-10bei/
|
| 67 |
|
| 68 |
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
|
| 69 |
Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
|
|
|
|
| 38 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 39 |
- Method: QLoRA (4-bit)
|
| 40 |
- Max sequence length: 512
|
| 41 |
+
- Epochs: 1
|
| 42 |
+
- Learning rate: 1e-04
|
| 43 |
+
- LoRA: r=32, alpha=64
|
| 44 |
|
| 45 |
## Usage
|
| 46 |
|
|
|
|
| 63 |
|
| 64 |
## Sources & Terms (IMPORTANT)
|
| 65 |
|
| 66 |
+
Training data: ['u-10bei/structured_data_with_cot_dataset_512', 'u-10bei/structured_data_with_cot_dataset_512_v2', 'u-10bei/structured_data_with_cot_dataset_512_v4', 'u-10bei/structured_data_with_cot_dataset_512_v5', 'u-10bei/structured_data_with_cot_dataset_v2']
|
| 67 |
|
| 68 |
Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
|
| 69 |
Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.
|
adapter_config.json
CHANGED
|
@@ -20,7 +20,7 @@
|
|
| 20 |
"layers_pattern": null,
|
| 21 |
"layers_to_transform": null,
|
| 22 |
"loftq_config": {},
|
| 23 |
-
"lora_alpha":
|
| 24 |
"lora_bias": false,
|
| 25 |
"lora_dropout": 0.0,
|
| 26 |
"megatron_config": null,
|
|
@@ -29,16 +29,16 @@
|
|
| 29 |
"peft_type": "LORA",
|
| 30 |
"peft_version": "0.18.1",
|
| 31 |
"qalora_group_size": 16,
|
| 32 |
-
"r":
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
| 36 |
-
"o_proj",
|
| 37 |
-
"down_proj",
|
| 38 |
"up_proj",
|
| 39 |
-
"gate_proj",
|
| 40 |
"v_proj",
|
|
|
|
|
|
|
| 41 |
"k_proj",
|
|
|
|
| 42 |
"q_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
|
|
|
| 20 |
"layers_pattern": null,
|
| 21 |
"layers_to_transform": null,
|
| 22 |
"loftq_config": {},
|
| 23 |
+
"lora_alpha": 64,
|
| 24 |
"lora_bias": false,
|
| 25 |
"lora_dropout": 0.0,
|
| 26 |
"megatron_config": null,
|
|
|
|
| 29 |
"peft_type": "LORA",
|
| 30 |
"peft_version": "0.18.1",
|
| 31 |
"qalora_group_size": 16,
|
| 32 |
+
"r": 32,
|
| 33 |
"rank_pattern": {},
|
| 34 |
"revision": null,
|
| 35 |
"target_modules": [
|
|
|
|
|
|
|
| 36 |
"up_proj",
|
|
|
|
| 37 |
"v_proj",
|
| 38 |
+
"o_proj",
|
| 39 |
+
"gate_proj",
|
| 40 |
"k_proj",
|
| 41 |
+
"down_proj",
|
| 42 |
"q_proj"
|
| 43 |
],
|
| 44 |
"target_parameters": null,
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87158f985ea3df9cecafe79a9eb0cc460b9ace2f5ebdd889befd0a6711811ed9
|
| 3 |
+
size 264308896
|
all_experiments_details.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|