Update README.md
Browse files
README.md
CHANGED
|
@@ -20,6 +20,7 @@ This is a version of Meta's [chat instruction-tuned Llama 2](https://huggingface
|
|
| 20 |
|
| 21 |
The dataset is a combination of [Evol-Instruct-Code-80k-v1](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) from [nikrosh](https://huggingface.co/nickrosh), a replication of the Evol-Instruct-Code as described in the [WizardCoder](https://arxiv.org/pdf/2306.08568.pdf) paper, and [Teknium](https://huggingface.co/teknium)'s [GPTeacher](https://github.com/teknium1/GPTeacher/blob/main/Codegen/codegen-instruct.json). Special thanks to these folks for putting these datasets together.
|
| 22 |
|
|
|
|
| 23 |
|
| 24 |
## Prompt Format
|
| 25 |
The reccomended model prompt is a variant of the standard Llama 2 format:
|
|
|
|
| 20 |
|
| 21 |
The dataset is a combination of [Evol-Instruct-Code-80k-v1](https://huggingface.co/datasets/nickrosh/Evol-Instruct-Code-80k-v1) from [nikrosh](https://huggingface.co/nickrosh), a replication of the Evol-Instruct-Code as described in the [WizardCoder](https://arxiv.org/pdf/2306.08568.pdf) paper, and [Teknium](https://huggingface.co/teknium)'s [GPTeacher](https://github.com/teknium1/GPTeacher/blob/main/Codegen/codegen-instruct.json). Special thanks to these folks for putting these datasets together.
|
| 22 |
|
| 23 |
+
Our fine-tuning process involved learning QLoRA weights over 6 hours on a single A100. We merged the adapter weights into the pre-trained model.
|
| 24 |
|
| 25 |
## Prompt Format
|
| 26 |
The reccomended model prompt is a variant of the standard Llama 2 format:
|