Update README.md
Browse files
README.md
CHANGED
|
@@ -1,8 +1,21 @@
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
-
## Training procedure
|
| 5 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
|
| 7 |
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
- quant_method: bitsandbytes
|
|
@@ -15,7 +28,8 @@ The following `bitsandbytes` quantization config was used during training:
|
|
| 15 |
- bnb_4bit_quant_type: fp4
|
| 16 |
- bnb_4bit_use_double_quant: False
|
| 17 |
- bnb_4bit_compute_dtype: float32
|
|
|
|
| 18 |
### Framework versions
|
| 19 |
|
| 20 |
|
| 21 |
-
- PEFT 0.5.0.dev0
|
|
|
|
| 1 |
---
|
| 2 |
library_name: peft
|
| 3 |
+
license: cc-by-3.0
|
| 4 |
+
datasets:
|
| 5 |
+
- Gustrd/dolly-15k-hippo-translated-pt-12k
|
| 6 |
+
language:
|
| 7 |
+
- pt
|
| 8 |
---
|
|
|
|
| 9 |
|
| 10 |
+
### Cabra: A portuguese finetuned instruction Open-LLaMA
|
| 11 |
+
|
| 12 |
+
LoRA adapter created with the procedures detailed at the GitHub repository: https://github.com/gustrd/cabra .
|
| 13 |
+
|
| 14 |
+
This training was done at 2 epochs using two T4 at Kaggle.
|
| 15 |
+
|
| 16 |
+
This LoRA adapter was created following the procedure:
|
| 17 |
+
|
| 18 |
+
## Training procedure
|
| 19 |
|
| 20 |
The following `bitsandbytes` quantization config was used during training:
|
| 21 |
- quant_method: bitsandbytes
|
|
|
|
| 28 |
- bnb_4bit_quant_type: fp4
|
| 29 |
- bnb_4bit_use_double_quant: False
|
| 30 |
- bnb_4bit_compute_dtype: float32
|
| 31 |
+
|
| 32 |
### Framework versions
|
| 33 |
|
| 34 |
|
| 35 |
+
- PEFT 0.5.0.dev0
|