Update Model Card
Browse files
README.md
CHANGED
|
@@ -23,9 +23,9 @@ This model is a fine-tuned version of google/gemma-2b on an SaikatM/Code-Platypu
|
|
| 23 |
|
| 24 |
### Model Description
|
| 25 |
|
| 26 |
-
- **Finetuned from model
|
| 27 |
|
| 28 |
-
### Model Sources
|
| 29 |
|
| 30 |
Training Code can be found here:
|
| 31 |
|
|
@@ -41,11 +41,10 @@ Source Dataset: https://huggingface.co/datasets/garage-bAInd/Open-Platypus
|
|
| 41 |
|
| 42 |
Used QLoRA from PEFT and used SFTTrainer.
|
| 43 |
|
| 44 |
-
#### Preprocessing [
|
| 45 |
|
| 46 |
From the Open-Platypus dataset filtering-out rows which has leetcode_ne in it's data_source column.
|
| 47 |
|
| 48 |
-
|
| 49 |
#### Training Hyperparameters
|
| 50 |
|
| 51 |
LoraConfig(
|
|
@@ -88,7 +87,7 @@ SFTTrainer(
|
|
| 88 |
args=training_arguments,
|
| 89 |
)
|
| 90 |
|
| 91 |
-
#### Speeds, Sizes, Times
|
| 92 |
|
| 93 |
Took around 1 hour to train.
|
| 94 |
|
|
|
|
| 23 |
|
| 24 |
### Model Description
|
| 25 |
|
| 26 |
+
- **Finetuned from model:** google/gemma-2b
|
| 27 |
|
| 28 |
+
### Model Sources
|
| 29 |
|
| 30 |
Training Code can be found here:
|
| 31 |
|
|
|
|
| 41 |
|
| 42 |
Used QLoRA from PEFT and used SFTTrainer.
|
| 43 |
|
| 44 |
+
#### Preprocessing [
|
| 45 |
|
| 46 |
From the Open-Platypus dataset filtering-out rows which has leetcode_ne in it's data_source column.
|
| 47 |
|
|
|
|
| 48 |
#### Training Hyperparameters
|
| 49 |
|
| 50 |
LoraConfig(
|
|
|
|
| 87 |
args=training_arguments,
|
| 88 |
)
|
| 89 |
|
| 90 |
+
#### Speeds, Sizes, Times
|
| 91 |
|
| 92 |
Took around 1 hour to train.
|
| 93 |
|