Create config.json
Browse files- config.json +29 -0
config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_config": {
|
| 3 |
+
"architectures": ["PhiForSequenceClassification"],
|
| 4 |
+
"model_type": "phi",
|
| 5 |
+
"name": "Waggerra/classifier",
|
| 6 |
+
"base_model": "microsoft/phi-3",
|
| 7 |
+
"fine_tuned": true
|
| 8 |
+
},
|
| 9 |
+
"inference_config": {
|
| 10 |
+
"temperature": 0.7,
|
| 11 |
+
"top_p": 0.9,
|
| 12 |
+
"max_length": 2048,
|
| 13 |
+
"do_sample": true
|
| 14 |
+
},
|
| 15 |
+
"training_config": {
|
| 16 |
+
"learning_rate": 2e-5,
|
| 17 |
+
"num_train_epochs": 3,
|
| 18 |
+
"per_device_train_batch_size": 4,
|
| 19 |
+
"gradient_accumulation_steps": 4
|
| 20 |
+
},
|
| 21 |
+
"metadata": {
|
| 22 |
+
"author": "Waggerra",
|
| 23 |
+
"model_name": "classifier",
|
| 24 |
+
"description": "Phi-3 3B model fine-tuned for classification tasks",
|
| 25 |
+
"tags": ["classification", "phi-3", "fine-tuned"],
|
| 26 |
+
"license": "mit",
|
| 27 |
+
"language": ["en"]
|
| 28 |
+
}
|
| 29 |
+
}
|