Instructions to use ydshieh/tiny-random-gptj-for-sequence-classification with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ydshieh/tiny-random-gptj-for-sequence-classification with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="ydshieh/tiny-random-gptj-for-sequence-classification")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("ydshieh/tiny-random-gptj-for-sequence-classification") model = AutoModelForSequenceClassification.from_pretrained("ydshieh/tiny-random-gptj-for-sequence-classification") - Notebooks
- Google Colab
- Kaggle
Update config.json (rotary dim should be smaller for tests)
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -24,7 +24,7 @@
|
|
| 24 |
"n_positions": 512,
|
| 25 |
"pad_token_id": 98,
|
| 26 |
"resid_pdrop": 0.0,
|
| 27 |
-
"rotary_dim":
|
| 28 |
"scale_attn_weights": true,
|
| 29 |
"tie_word_embeddings": false,
|
| 30 |
"torch_dtype": "float32",
|
|
|
|
| 24 |
"n_positions": 512,
|
| 25 |
"pad_token_id": 98,
|
| 26 |
"resid_pdrop": 0.0,
|
| 27 |
+
"rotary_dim": 8,
|
| 28 |
"scale_attn_weights": true,
|
| 29 |
"tie_word_embeddings": false,
|
| 30 |
"torch_dtype": "float32",
|