Text Generation
PEFT
Safetensors
English
qlora
lora
structured-output
nikeda commited on
Commit
e1ebe74
·
verified ·
1 Parent(s): 787e043

Upload LoRA adapter (README written by author)

Browse files
Files changed (3) hide show
  1. README.md +3 -3
  2. adapter_config.json +3 -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/structured_data_with_cot_dataset_512_v5
5
  language:
6
  - en
7
  license: apache-2.0
@@ -34,7 +34,7 @@ while intermediate reasoning (Chain-of-Thought) is masked.
34
  - Base model: Qwen/Qwen3-4B-Instruct-2507
35
  - Method: QLoRA (4-bit)
36
  - Max sequence length: 512
37
- - Epochs: 2
38
  - Learning rate: 2e-05
39
  - LoRA: r=32, alpha=64
40
 
@@ -59,7 +59,7 @@ model = PeftModel.from_pretrained(model, adapter)
59
 
60
  ## Sources & Terms (IMPORTANT)
61
 
62
- Training data: u-10bei/structured_data_with_cot_dataset_512_v5
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
+ - daichira/structured-hard-sft-4k
5
  language:
6
  - en
7
  license: apache-2.0
 
34
  - Base model: Qwen/Qwen3-4B-Instruct-2507
35
  - Method: QLoRA (4-bit)
36
  - Max sequence length: 512
37
+ - Epochs: 1
38
  - Learning rate: 2e-05
39
  - LoRA: r=32, alpha=64
40
 
 
59
 
60
  ## Sources & Terms (IMPORTANT)
61
 
62
+ Training data: daichira/structured-hard-sft-4k
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_config.json CHANGED
@@ -34,12 +34,12 @@
34
  "revision": null,
35
  "target_modules": [
36
  "gate_proj",
 
37
  "v_proj",
38
  "k_proj",
39
- "q_proj",
40
- "o_proj",
41
  "up_proj",
42
- "down_proj"
43
  ],
44
  "target_parameters": null,
45
  "task_type": "CAUSAL_LM",
 
34
  "revision": null,
35
  "target_modules": [
36
  "gate_proj",
37
+ "q_proj",
38
  "v_proj",
39
  "k_proj",
40
+ "down_proj",
 
41
  "up_proj",
42
+ "o_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 sha256:0c237e01f6eb66e7c247cc78a45a3290b43c04b76c0ce909f4282fd64fe72316
3
  size 264308896
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0ce57123d844dcbca8154917c2f85fd95da86ab2ed1ac9f5cd35e00af0eabb
3
  size 264308896