Instructions to use baseten/RandomQwen2ForSequenceClassification-0.5B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use baseten/RandomQwen2ForSequenceClassification-0.5B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="baseten/RandomQwen2ForSequenceClassification-0.5B")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("baseten/RandomQwen2ForSequenceClassification-0.5B") model = AutoModelForSequenceClassification.from_pretrained("baseten/RandomQwen2ForSequenceClassification-0.5B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update config.json
Browse files- config.json +1 -1
config.json
CHANGED
|
@@ -18,7 +18,7 @@
|
|
| 18 |
"hidden_size": 896,
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
"intermediate_size": 4864,
|
| 21 |
-
"max_position_embeddings":
|
| 22 |
"max_window_layers": 21,
|
| 23 |
"model_type": "qwen2",
|
| 24 |
"num_attention_heads": 14,
|
|
|
|
| 18 |
"hidden_size": 896,
|
| 19 |
"initializer_range": 0.02,
|
| 20 |
"intermediate_size": 4864,
|
| 21 |
+
"max_position_embeddings": 16384,
|
| 22 |
"max_window_layers": 21,
|
| 23 |
"model_type": "qwen2",
|
| 24 |
"num_attention_heads": 14,
|