Instructions to use yamanara/structured-output-lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use yamanara/structured-output-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("unsloth/qwen3-4b-instruct-2507-unsloth-bnb-4bit") model = PeftModel.from_pretrained(base_model, "yamanara/structured-output-lora") - Notebooks
- Google Colab
- Kaggle
Upload LoRA adapter (README written by author)
Browse files- README.md +1 -1
- adapter_model.safetensors +1 -1
README.md
CHANGED
|
@@ -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: 2
|
| 38 |
- Learning rate: 5e-05
|
| 39 |
- LoRA: r=8, alpha=16
|
|
|
|
| 33 |
|
| 34 |
- Base model: Qwen/Qwen3-4B-Instruct-2507
|
| 35 |
- Method: QLoRA (4-bit)
|
| 36 |
+
- Max sequence length: 1024
|
| 37 |
- Epochs: 2
|
| 38 |
- Learning rate: 5e-05
|
| 39 |
- LoRA: r=8, alpha=16
|
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14165120
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d2fd4b12bc849a4dd5e09da46eaf895410495b566c1108fcdaaba210aeadad7
|
| 3 |
size 14165120
|