Update README.md
Browse files
README.md
CHANGED
|
@@ -1,9 +1,19 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
-
## Training procedure
|
| 5 |
|
|
|
|
|
|
|
| 6 |
|
|
|
|
| 7 |
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
- load_in_8bit: False
|
| 9 |
- load_in_4bit: True
|
|
@@ -17,4 +27,4 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 17 |
### Framework versions
|
| 18 |
|
| 19 |
|
| 20 |
-
- PEFT 0.4.0
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
+
license: mit
|
| 4 |
+
datasets:
|
| 5 |
+
- yahma/alpaca-cleaned
|
| 6 |
+
pipeline_tag: text-generation
|
| 7 |
+
tags:
|
| 8 |
+
- Text Generation
|
| 9 |
+
- LLaMA2
|
| 10 |
+
- LLM
|
| 11 |
---
|
|
|
|
| 12 |
|
| 13 |
+
## Quantized LLaMA2
|
| 14 |
+
**quantized-llama2-alpaca** is a fine-tuned version of the **LLaMA2** (Llama-2-7b-hf) model on the **Alpaca** dataset using **QLoRA**.
|
| 15 |
|
| 16 |
+
## Training procedure
|
| 17 |
The following `bitsandbytes` quantization config was used during training:
|
| 18 |
- load_in_8bit: False
|
| 19 |
- load_in_4bit: True
|
|
|
|
| 27 |
### Framework versions
|
| 28 |
|
| 29 |
|
| 30 |
+
- PEFT 0.4.0
|