Text Classification
PEFT
Safetensors
English
argument-mining
argument-detection
computational-social-science
llama
lora
wiba
Instructions to use armaniii/WIBA-Detect-V1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use armaniii/WIBA-Detect-V1 with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Meta-Llama-3-8B") model = PeftModel.from_pretrained(base_model, "armaniii/WIBA-Detect-V1") - Notebooks
- Google Colab
- Kaggle
Update adapter_config.json (modern PEFT format conversion)
Browse files- adapter_config.json +3 -2
adapter_config.json
CHANGED
|
@@ -13,7 +13,9 @@
|
|
| 13 |
"lora_dropout": 0.05,
|
| 14 |
"megatron_config": null,
|
| 15 |
"megatron_core": "megatron.core",
|
| 16 |
-
"modules_to_save":
|
|
|
|
|
|
|
| 17 |
"peft_type": "LORA",
|
| 18 |
"r": 8,
|
| 19 |
"rank_pattern": {},
|
|
@@ -25,7 +27,6 @@
|
|
| 25 |
"k_proj",
|
| 26 |
"v_proj",
|
| 27 |
"q_proj",
|
| 28 |
-
"score",
|
| 29 |
"up_proj"
|
| 30 |
],
|
| 31 |
"task_type": "SEQ_CLS"
|
|
|
|
| 13 |
"lora_dropout": 0.05,
|
| 14 |
"megatron_config": null,
|
| 15 |
"megatron_core": "megatron.core",
|
| 16 |
+
"modules_to_save": [
|
| 17 |
+
"score"
|
| 18 |
+
],
|
| 19 |
"peft_type": "LORA",
|
| 20 |
"r": 8,
|
| 21 |
"rank_pattern": {},
|
|
|
|
| 27 |
"k_proj",
|
| 28 |
"v_proj",
|
| 29 |
"q_proj",
|
|
|
|
| 30 |
"up_proj"
|
| 31 |
],
|
| 32 |
"task_type": "SEQ_CLS"
|