Instructions to use philschmid/Infinity_gpu_MiniLM_L6_H384_uncased_sst2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use philschmid/Infinity_gpu_MiniLM_L6_H384_uncased_sst2 with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("philschmid/Infinity_gpu_MiniLM_L6_H384_uncased_sst2", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
a13e13f
1
Parent(s): 5b4c1da
Upload config.json
Browse files- config.json +1 -0
config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"infrastructure": {"accelerator": "gpu", "hardware": "nvidia"}, "pipeline": {"client": {"port": 8001, "url": "localhost", "use_tls": false}, "name": "philschmid__MiniLM_L6_H384_uncased_sst2", "task": "sequence_classification", "tokenizer": "./tokenizer.json", "version": "1"}}
|