Instructions to use erickdp/beto-base-peft-p-tuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use erickdp/beto-base-peft-p-tuning with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("dccuchile/bert-base-spanish-wwm-uncased") model = PeftModel.from_pretrained(base_model, "erickdp/beto-base-peft-p-tuning") - Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- README.md +9 -0
- adapter_config.json +17 -0
- adapter_model.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
### Framework versions
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
- PEFT 0.5.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "dccuchile/bert-base-spanish-wwm-uncased",
|
| 4 |
+
"encoder_dropout": 0.0,
|
| 5 |
+
"encoder_hidden_size": 128,
|
| 6 |
+
"encoder_num_layers": 2,
|
| 7 |
+
"encoder_reparameterization_type": "MLP",
|
| 8 |
+
"inference_mode": true,
|
| 9 |
+
"num_attention_heads": 12,
|
| 10 |
+
"num_layers": 12,
|
| 11 |
+
"num_transformer_submodules": 1,
|
| 12 |
+
"num_virtual_tokens": 20,
|
| 13 |
+
"peft_type": "P_TUNING",
|
| 14 |
+
"revision": null,
|
| 15 |
+
"task_type": "SEQ_CLS",
|
| 16 |
+
"token_dim": 768
|
| 17 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1d3639b9121565c5eaa1854850e857547c0aeaa5d50553993b53f8e3ce44640
|
| 3 |
+
size 72065
|