Commit
•
ffa66e6
1
Parent(s):
810c426
Update README.md
Browse files
README.md
CHANGED
@@ -1,9 +1,39 @@
|
|
1 |
---
|
2 |
library_name: peft
|
|
|
|
|
|
|
3 |
---
|
4 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
|
|
|
|
|
6 |
|
|
|
|
|
7 |
The following `bitsandbytes` quantization config was used during training:
|
8 |
- quant_method: bitsandbytes
|
9 |
- load_in_8bit: True
|
@@ -15,7 +45,6 @@ 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
|
|
|
1 |
---
|
2 |
library_name: peft
|
3 |
+
license: mit
|
4 |
+
language:
|
5 |
+
- ar
|
6 |
---
|
7 |
+
BLOOM-7B Arabic [LAPT + CLP+]
|
8 |
+
===
|
9 |
+
|
10 |
+
## How to use
|
11 |
+
```python
|
12 |
+
from peft import AutoPeftModelForCausalLM
|
13 |
+
from transformers import AutoTokenizer
|
14 |
+
|
15 |
+
model = AutoPeftModelForCausalLM.from_pretrained(
|
16 |
+
"atsuki-yamaguchi/bloom-7b1-clpp-ar"
|
17 |
+
)
|
18 |
+
```
|
19 |
+
|
20 |
+
## Citation
|
21 |
+
```
|
22 |
+
@article{yamaguchi2024empirical,
|
23 |
+
title={An Empirical Study on Cross-lingual Vocabulary Adaptation for Efficient Generative {LLM} Inference},
|
24 |
+
author={Atsuki Yamaguchi and Aline Villavicencio and Nikolaos Aletras},
|
25 |
+
journal={ArXiv},
|
26 |
+
year={2024},
|
27 |
+
volume={abs/2402.10712},
|
28 |
+
url={https://arxiv.org/abs/2402.10712}
|
29 |
+
}
|
30 |
+
```
|
31 |
|
32 |
+
## Link
|
33 |
+
For more details, please visit https://github.com/gucci-j/llm-cva
|
34 |
|
35 |
+
|
36 |
+
## Training procedure
|
37 |
The following `bitsandbytes` quantization config was used during training:
|
38 |
- quant_method: bitsandbytes
|
39 |
- load_in_8bit: True
|
|
|
45 |
- bnb_4bit_quant_type: fp4
|
46 |
- bnb_4bit_use_double_quant: False
|
47 |
- bnb_4bit_compute_dtype: float32
|
48 |
+
|
49 |
### Framework versions
|
50 |
+
- PEFT 0.5.0
|
|
|
|