Instructions to use jogonba2/POCTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jogonba2/POCTS with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # 'pip install "transformers<5.0.0' from transformers import pipeline pipe = pipeline("summarization", model="jogonba2/POCTS")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("jogonba2/POCTS") model = AutoModelForSeq2SeqLM.from_pretrained("jogonba2/POCTS") - Notebooks
- Google Colab
- Kaggle
José Ángel González commited on
Commit ·
26020cd
1
Parent(s): 4509e78
Update config.json
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -48,9 +48,9 @@
|
|
| 48 |
"scale_embedding": false,
|
| 49 |
"task_specific_params": {
|
| 50 |
"summarization": {
|
| 51 |
-
"length_penalty":
|
| 52 |
"max_length": 128,
|
| 53 |
-
"min_length":
|
| 54 |
"num_beams": 4
|
| 55 |
},
|
| 56 |
"summarization_cnn": {
|
|
|
|
| 48 |
"scale_embedding": false,
|
| 49 |
"task_specific_params": {
|
| 50 |
"summarization": {
|
| 51 |
+
"length_penalty": 2.0,
|
| 52 |
"max_length": 128,
|
| 53 |
+
"min_length": 15,
|
| 54 |
"num_beams": 4
|
| 55 |
},
|
| 56 |
"summarization_cnn": {
|