Instructions to use Ray2333/gpt2-large-harmless-reward_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Ray2333/gpt2-large-harmless-reward_model with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="Ray2333/gpt2-large-harmless-reward_model")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("Ray2333/gpt2-large-harmless-reward_model") model = AutoModelForSequenceClassification.from_pretrained("Ray2333/gpt2-large-harmless-reward_model", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload config.json
Browse files- config.json +3 -3
config.json
CHANGED
|
@@ -1,5 +1,5 @@
|
|
| 1 |
{
|
| 2 |
-
"_name_or_path": "/
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2ForSequenceClassification"
|
|
@@ -38,8 +38,8 @@
|
|
| 38 |
"max_length": 50
|
| 39 |
}
|
| 40 |
},
|
| 41 |
-
"torch_dtype": "
|
| 42 |
-
"transformers_version": "4.
|
| 43 |
"use_cache": true,
|
| 44 |
"vocab_size": 50257
|
| 45 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "Ray2333/gpt2-large-harmless-reward_model",
|
| 3 |
"activation_function": "gelu_new",
|
| 4 |
"architectures": [
|
| 5 |
"GPT2ForSequenceClassification"
|
|
|
|
| 38 |
"max_length": 50
|
| 39 |
}
|
| 40 |
},
|
| 41 |
+
"torch_dtype": "bfloat16",
|
| 42 |
+
"transformers_version": "4.36.2",
|
| 43 |
"use_cache": true,
|
| 44 |
"vocab_size": 50257
|
| 45 |
}
|