Instructions to use Junnos/lucky-vicky with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Junnos/lucky-vicky with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("yanolja/EEVE-Korean-10.8B-v1.0") model = PeftModel.from_pretrained(base_model, "Junnos/lucky-vicky") - Notebooks
- Google Colab
- Kaggle
Model save
Browse files
README.md
CHANGED
|
@@ -4,8 +4,8 @@ library_name: peft
|
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- trl
|
| 7 |
-
- dpo
|
| 8 |
- sft
|
|
|
|
| 9 |
- generated_from_trainer
|
| 10 |
model-index:
|
| 11 |
- name: lucky-vicky
|
|
@@ -45,7 +45,7 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
-
- num_epochs:
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|
|
|
|
| 4 |
license: apache-2.0
|
| 5 |
tags:
|
| 6 |
- trl
|
|
|
|
| 7 |
- sft
|
| 8 |
+
- dpo
|
| 9 |
- generated_from_trainer
|
| 10 |
model-index:
|
| 11 |
- name: lucky-vicky
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: cosine
|
| 47 |
- lr_scheduler_warmup_ratio: 0.03
|
| 48 |
+
- num_epochs: 3
|
| 49 |
|
| 50 |
### Training results
|
| 51 |
|