Feature Extraction
Transformers
TensorBoard
Safetensors
English
captionbert_structured_rotary
sentence-similarity
consensus-distillation
rotary-embeddings
custom_code
Instructions to use AbstractPhil/captionbert-8192-rotary with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AbstractPhil/captionbert-8192-rotary with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="AbstractPhil/captionbert-8192-rotary", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("AbstractPhil/captionbert-8192-rotary", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Preserve complete selected remote AutoModel Colab console
Browse files
campaigns/structured-20261106/validation/deployment-colab/20261106T204053Z/console.log
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
GPU memory ceiling 92.00 GB total; allocator allowance 90.61 GB
|
| 2 |
+
|
| 3 |
+
Loading weights: 0%| | 0/157 [00:00<?, ?it/s]
|
| 4 |
+
Loading weights: 100%|██████████| 157/157 [00:00<00:00, 15335.49it/s]
|
| 5 |
+
[transformers] `use_return_dict` is deprecated! Use `return_dict` instead!
|
| 6 |
+
Parity natural/fp32: {'case': 'natural', 'precision': 'fp32', 'input_shape': [2, 11], 'embedding_shape': [2, 768], 'hidden_shape': [2, 11, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.16567078699881677}
|
| 7 |
+
Parity all_padding/fp32: {'case': 'all_padding', 'precision': 'fp32', 'input_shape': [2, 17], 'embedding_shape': [2, 768], 'hidden_shape': [2, 17, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.019933960000344086}
|
| 8 |
+
Parity synthetic_1x1/fp32: {'case': 'synthetic_1x1', 'precision': 'fp32', 'input_shape': [1, 1], 'embedding_shape': [1, 768], 'hidden_shape': [1, 1, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.056073969000863144}
|
| 9 |
+
Parity synthetic_2x17/fp32: {'case': 'synthetic_2x17', 'precision': 'fp32', 'input_shape': [2, 17], 'embedding_shape': [2, 768], 'hidden_shape': [2, 17, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.019162890002917266}
|
| 10 |
+
Parity synthetic_3x128/fp32: {'case': 'synthetic_3x128', 'precision': 'fp32', 'input_shape': [3, 128], 'embedding_shape': [3, 768], 'hidden_shape': [3, 128, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.019288038998638513}
|
| 11 |
+
Parity synthetic_1x512/fp32: {'case': 'synthetic_1x512', 'precision': 'fp32', 'input_shape': [1, 512], 'embedding_shape': [1, 768], 'hidden_shape': [1, 512, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.019747980000829557}
|
| 12 |
+
Parity boundary_shape_1025/fp32: {'case': 'boundary_shape_1025', 'precision': 'fp32', 'input_shape': [1, 1025], 'embedding_shape': [1, 768], 'hidden_shape': [1, 1025, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.02409016999808955}
|
| 13 |
+
Parity boundary_shape_8192/fp32: {'case': 'boundary_shape_8192', 'precision': 'fp32', 'input_shape': [1, 8192], 'embedding_shape': [1, 768], 'hidden_shape': [1, 8192, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.19234563700229046}
|
| 14 |
+
Parity natural/fp16_autocast: {'case': 'natural', 'precision': 'fp16_autocast', 'input_shape': [2, 11], 'embedding_shape': [2, 768], 'hidden_shape': [2, 11, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.08385088800059748}
|
| 15 |
+
Parity all_padding/fp16_autocast: {'case': 'all_padding', 'precision': 'fp16_autocast', 'input_shape': [2, 17], 'embedding_shape': [2, 768], 'hidden_shape': [2, 17, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.019784469997830456}
|
| 16 |
+
Parity natural/bf16_autocast: {'case': 'natural', 'precision': 'bf16_autocast', 'input_shape': [2, 11], 'embedding_shape': [2, 768], 'hidden_shape': [2, 11, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.07453705900115892}
|
| 17 |
+
Parity all_padding/bf16_autocast: {'case': 'all_padding', 'precision': 'bf16_autocast', 'input_shape': [2, 17], 'embedding_shape': [2, 768], 'hidden_shape': [2, 17, 512], 'max_embedding_delta': 0.0, 'max_hidden_delta': 0.0, 'seconds': 0.020809778998227557}
|
| 18 |
+
Independent deployment verification passed: /content/captionbert-deployment-validation/default-remote-parity-20261106T204053Z.json
|
| 19 |
+
SELECTED REMOTE AUTOMODEL COLAB CHECK COMPLETE; no optimizer or training
|