Update model card README with dataset link
Browse files
README.md
CHANGED
|
@@ -1,9 +1,12 @@
|
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
tags:
|
| 4 |
- qlora
|
| 5 |
- finetuned
|
| 6 |
- transformers
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# Uber-assistant QLoRA Adapter
|
|
@@ -14,7 +17,7 @@ This is a LoRA adapter finetuned on Uber Annual Report 2024
|
|
| 14 |
meta-llama/Llama-3.1-8B-Instruct
|
| 15 |
|
| 16 |
## Dataset
|
| 17 |
-
Uber Annual Report 2024
|
| 18 |
|
| 19 |
## Training Hyperparameters
|
| 20 |
- LoRA rank: 16
|
|
@@ -31,8 +34,8 @@ from transformers import AutoModelForCausalLM, AutoTokenizer
|
|
| 31 |
from peft import PeftModel
|
| 32 |
|
| 33 |
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
|
| 34 |
-
model = PeftModel.from_pretrained(base_model, "
|
| 35 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
| 36 |
```
|
| 37 |
|
| 38 |
## License & Attribution
|
|
|
|
| 1 |
+
|
| 2 |
---
|
| 3 |
license: apache-2.0
|
| 4 |
tags:
|
| 5 |
- qlora
|
| 6 |
- finetuned
|
| 7 |
- transformers
|
| 8 |
+
datasets:
|
| 9 |
+
- vishalgimhan/uber-report-2024-dataset
|
| 10 |
---
|
| 11 |
|
| 12 |
# Uber-assistant QLoRA Adapter
|
|
|
|
| 17 |
meta-llama/Llama-3.1-8B-Instruct
|
| 18 |
|
| 19 |
## Dataset
|
| 20 |
+
Finetuned using the [Uber Annual Report 2024 Dataset](https://huggingface.co/datasets/vishalgimhan/uber-report-2024-dataset)
|
| 21 |
|
| 22 |
## Training Hyperparameters
|
| 23 |
- LoRA rank: 16
|
|
|
|
| 34 |
from peft import PeftModel
|
| 35 |
|
| 36 |
base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct")
|
| 37 |
+
model = PeftModel.from_pretrained(base_model, "vishalgimhan/uber-assistant")
|
| 38 |
+
tokenizer = AutoTokenizer.from_pretrained("vishalgimhan/uber-assistant")
|
| 39 |
```
|
| 40 |
|
| 41 |
## License & Attribution
|