Instructions to use bilkultheek/Cold-Data-LLama-2-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use bilkultheek/Cold-Data-LLama-2-7B with PEFT:
from peft import PeftModel from transformers import AutoModelForSequenceClassification base_model = AutoModelForSequenceClassification.from_pretrained("meta-llama/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "bilkultheek/Cold-Data-LLama-2-7B") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files
README.md
CHANGED
|
@@ -36,11 +36,11 @@ More information needed
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.01
|
| 39 |
-
- train_batch_size:
|
| 40 |
-
- eval_batch_size:
|
| 41 |
- seed: 42
|
| 42 |
-
- gradient_accumulation_steps:
|
| 43 |
-
- total_train_batch_size:
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_ratio: 0.03
|
|
|
|
| 36 |
|
| 37 |
The following hyperparameters were used during training:
|
| 38 |
- learning_rate: 0.01
|
| 39 |
+
- train_batch_size: 16
|
| 40 |
+
- eval_batch_size: 16
|
| 41 |
- seed: 42
|
| 42 |
+
- gradient_accumulation_steps: 8
|
| 43 |
+
- total_train_batch_size: 128
|
| 44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 45 |
- lr_scheduler_type: cosine
|
| 46 |
- lr_scheduler_warmup_ratio: 0.03
|