Instructions to use arnavgrg/codealpaca-qlora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use arnavgrg/codealpaca-qlora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-2-7b-hf") model = PeftModel.from_pretrained(base_model, "arnavgrg/codealpaca-qlora") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -27,7 +27,7 @@ inference:
|
|
| 27 |
|
| 28 |
This model was fine-tuned using [Predibase](https://predibase.com/), the first low-code AI platform for engineers.
|
| 29 |
I fine-tuned base Llama-2-7b using LoRA with 4 bit quantization on a single T4 GPU, which cost approximately $3 to train
|
| 30 |
-
on Predibase.
|
| 31 |
|
| 32 |
Dataset and training parameters are borrowed from: https://github.com/sahil280114/codealpaca,
|
| 33 |
but all of these parameters including DeepSpeed can be directly used with [Ludwig](https://ludwig.ai/latest/), the open-source
|
|
|
|
| 27 |
|
| 28 |
This model was fine-tuned using [Predibase](https://predibase.com/), the first low-code AI platform for engineers.
|
| 29 |
I fine-tuned base Llama-2-7b using LoRA with 4 bit quantization on a single T4 GPU, which cost approximately $3 to train
|
| 30 |
+
on Predibase. Try out our free Predibase trial [here](https://predibase.com/free-trial).
|
| 31 |
|
| 32 |
Dataset and training parameters are borrowed from: https://github.com/sahil280114/codealpaca,
|
| 33 |
but all of these parameters including DeepSpeed can be directly used with [Ludwig](https://ludwig.ai/latest/), the open-source
|