Commit
•
e6c6b7a
1
Parent(s):
60157e6
Librarian Bot: Add base_model information to model (#1)
Browse files- Librarian Bot: Add base_model information to model (3df931a4e7d3668d5309cfb37ceea10cb8c6a107)
Co-authored-by: Librarian Bot (Bot) <librarian-bot@users.noreply.huggingface.co>
README.md
CHANGED
|
@@ -1,12 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
license: cc-by-4.0
|
|
|
|
| 4 |
datasets:
|
| 5 |
- yahma/alpaca-cleaned
|
| 6 |
-
language:
|
| 7 |
-
- en
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
This represents the PEFT weights only. The base model is LLaMA 2. Instruction finetuning was done using 4 bit QLoRA on a single A100 GPU with the PEFT config as given below. The dataset used for this instruction finetuning process is a translated version of the cleaned alpaca dataset (translated using NLLB-1.3B).
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: cc-by-4.0
|
| 5 |
+
library_name: peft
|
| 6 |
datasets:
|
| 7 |
- yahma/alpaca-cleaned
|
|
|
|
|
|
|
| 8 |
metrics:
|
| 9 |
- accuracy
|
| 10 |
+
base_model: meta-llama/Llama-2-70b-hf
|
| 11 |
---
|
| 12 |
|
| 13 |
This represents the PEFT weights only. The base model is LLaMA 2. Instruction finetuning was done using 4 bit QLoRA on a single A100 GPU with the PEFT config as given below. The dataset used for this instruction finetuning process is a translated version of the cleaned alpaca dataset (translated using NLLB-1.3B).
|