Update README.md
Browse files
README.md
CHANGED
|
@@ -5,13 +5,15 @@ base_model:
|
|
| 5 |
tags:
|
| 6 |
- mergekit
|
| 7 |
- merge
|
| 8 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
---
|
| 10 |
-
# merge
|
| 11 |
-
|
| 12 |
-
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
| 13 |
|
| 14 |
-
## Merge Details
|
| 15 |
### Merge Method
|
| 16 |
|
| 17 |
This model was merged using the SLERP merge method.
|
|
@@ -46,3 +48,19 @@ parameters:
|
|
| 46 |
dtype: bfloat16
|
| 47 |
|
| 48 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
tags:
|
| 6 |
- mergekit
|
| 7 |
- merge
|
| 8 |
+
license: apache-2.0
|
| 9 |
+
language:
|
| 10 |
+
- en
|
| 11 |
+
- ar
|
| 12 |
+
- fr
|
| 13 |
+
library_name: transformers
|
| 14 |
+
pipeline_tag: text-generation
|
| 15 |
---
|
|
|
|
|
|
|
|
|
|
| 16 |
|
|
|
|
| 17 |
### Merge Method
|
| 18 |
|
| 19 |
This model was merged using the SLERP merge method.
|
|
|
|
| 48 |
dtype: bfloat16
|
| 49 |
|
| 50 |
```
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
## Usage :
|
| 55 |
+
|
| 56 |
+
```python
|
| 57 |
+
import torch
|
| 58 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
| 59 |
+
torch.set_default_device("cuda")
|
| 60 |
+
model = AutoModelForCausalLM.from_pretrained("ayoubkirouane/phi-2_MERGED", torch_dtype="auto", trust_remote_code=True)
|
| 61 |
+
tokenizer = AutoTokenizer.from_pretrained("ayoubkirouane/phi-2_MERGED", trust_remote_code=True)
|
| 62 |
+
inputs = tokenizer('What Machine Learning ? ', return_tensors="pt", return_attention_mask=False)
|
| 63 |
+
outputs = model.generate(**inputs, max_length=50)
|
| 64 |
+
text = tokenizer.batch_decode(outputs)[0]
|
| 65 |
+
print(text)
|
| 66 |
+
```
|