Instructions to use optimum/tiny_random_bert_neuron with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use optimum/tiny_random_bert_neuron with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="optimum/tiny_random_bert_neuron")# Load model directly from transformers import AutoTokenizer, AutoModel tokenizer = AutoTokenizer.from_pretrained("optimum/tiny_random_bert_neuron") model = AutoModel.from_pretrained("optimum/tiny_random_bert_neuron", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Optimum commited on
Upload config.json with huggingface_hub
Browse files- config.json +2 -2
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/tmp/
|
| 3 |
"architectures": [
|
| 4 |
"BertModel"
|
| 5 |
],
|
|
@@ -17,7 +17,7 @@
|
|
| 17 |
"auto_cast": null,
|
| 18 |
"auto_cast_type": null,
|
| 19 |
"compiler_type": "neuron-cc",
|
| 20 |
-
"compiler_version": "1.
|
| 21 |
"disable_fallback": false,
|
| 22 |
"disable_fast_relayout": false,
|
| 23 |
"dynamic_batch_size": false,
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "/tmp/tmprhp_6vei",
|
| 3 |
"architectures": [
|
| 4 |
"BertModel"
|
| 5 |
],
|
|
|
|
| 17 |
"auto_cast": null,
|
| 18 |
"auto_cast_type": null,
|
| 19 |
"compiler_type": "neuron-cc",
|
| 20 |
+
"compiler_version": "1.22.0.0+d4b4f5311",
|
| 21 |
"disable_fallback": false,
|
| 22 |
"disable_fast_relayout": false,
|
| 23 |
"dynamic_batch_size": false,
|