Instructions to use adrianjoheni/model_data10 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use adrianjoheni/model_data10 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="adrianjoheni/model_data10")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("adrianjoheni/model_data10") model = AutoModelForSeq2SeqLM.from_pretrained("adrianjoheni/model_data10", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update generation_config.json
Browse files- generation_config.json +2 -2
generation_config.json
CHANGED
|
@@ -7,8 +7,8 @@
|
|
| 7 |
"forced_bos_token_id": 0,
|
| 8 |
"forced_eos_token_id": 2,
|
| 9 |
"length_penalty": 2.0,
|
| 10 |
-
"max_length":
|
| 11 |
-
"min_length":
|
| 12 |
"no_repeat_ngram_size": 3,
|
| 13 |
"num_beams": 4,
|
| 14 |
"pad_token_id": 1,
|
|
|
|
| 7 |
"forced_bos_token_id": 0,
|
| 8 |
"forced_eos_token_id": 2,
|
| 9 |
"length_penalty": 2.0,
|
| 10 |
+
"max_length": 1024,
|
| 11 |
+
"min_length": 300,
|
| 12 |
"no_repeat_ngram_size": 3,
|
| 13 |
"num_beams": 4,
|
| 14 |
"pad_token_id": 1,
|