Update model card README
Browse files
README.md
CHANGED
|
@@ -1,18 +1,22 @@
|
|
| 1 |
-
---
|
| 2 |
-
{}
|
| 3 |
-
---
|
| 4 |
|
| 5 |
-
|
|
|
|
| 6 |
tags:
|
| 7 |
- qlora
|
| 8 |
- finetuned
|
|
|
|
| 9 |
---
|
| 10 |
|
| 11 |
-
|
|
|
|
|
|
|
| 12 |
|
| 13 |
-
# Base Model
|
| 14 |
meta-llama/Llama-3.1-8B-Instruct
|
| 15 |
|
|
|
|
|
|
|
|
|
|
| 16 |
## Training Hyperparameters
|
| 17 |
- LoRA rank: 16
|
| 18 |
- LoRA alpha: 32
|
|
@@ -21,10 +25,6 @@ meta-llama/Llama-3.1-8B-Instruct
|
|
| 21 |
- Batch size (effective): 16
|
| 22 |
- Max length: 512
|
| 23 |
|
| 24 |
-
# Dataset Details
|
| 25 |
-
dataset_split: "train"
|
| 26 |
-
dataset_size: 4615
|
| 27 |
-
|
| 28 |
## Usage
|
| 29 |
|
| 30 |
```python
|
|
@@ -35,6 +35,7 @@ base_model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instr
|
|
| 35 |
model = PeftModel.from_pretrained(base_model, "path/to/adapter")
|
| 36 |
tokenizer = AutoTokenizer.from_pretrained("path/to/adapter")
|
| 37 |
```
|
|
|
|
| 38 |
## License & Attribution
|
| 39 |
|
| 40 |
This adapter inherits the license of the base model and dataset. Check those licenses before use or redistribution.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
|
| 2 |
+
---
|
| 3 |
+
license: apache-2.0
|
| 4 |
tags:
|
| 5 |
- qlora
|
| 6 |
- finetuned
|
| 7 |
+
- transformers
|
| 8 |
---
|
| 9 |
|
| 10 |
+
# Uber-assistant QLoRA Adapter
|
| 11 |
+
|
| 12 |
+
This is a LoRA adapter finetuned on Uber Annual Report 2024
|
| 13 |
|
| 14 |
+
## Base Model
|
| 15 |
meta-llama/Llama-3.1-8B-Instruct
|
| 16 |
|
| 17 |
+
## Dataset
|
| 18 |
+
Uber Annual Report 2024
|
| 19 |
+
|
| 20 |
## Training Hyperparameters
|
| 21 |
- LoRA rank: 16
|
| 22 |
- LoRA alpha: 32
|
|
|
|
| 25 |
- Batch size (effective): 16
|
| 26 |
- Max length: 512
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
## Usage
|
| 29 |
|
| 30 |
```python
|
|
|
|
| 35 |
model = PeftModel.from_pretrained(base_model, "path/to/adapter")
|
| 36 |
tokenizer = AutoTokenizer.from_pretrained("path/to/adapter")
|
| 37 |
```
|
| 38 |
+
|
| 39 |
## License & Attribution
|
| 40 |
|
| 41 |
This adapter inherits the license of the base model and dataset. Check those licenses before use or redistribution.
|