Update README.md
Browse files
README.md
CHANGED
@@ -1,10 +1,27 @@
|
|
1 |
---
|
2 |
license: mit
|
3 |
-
datasets:
|
4 |
-
- MaxLSB/LeCarnet
|
5 |
language:
|
6 |
- fr
|
7 |
-
- en
|
8 |
pipeline_tag: text-generation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
9 |
---
|
10 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
license: mit
|
|
|
|
|
3 |
language:
|
4 |
- fr
|
|
|
5 |
pipeline_tag: text-generation
|
6 |
+
datasets:
|
7 |
+
- MaxLSB/LeCarnet
|
8 |
+
---
|
9 |
+
Model Trained on the [LeCarnet](https://huggingface.co/datasets/MaxLSB/LeCarnet) Dataset.
|
10 |
+
|
11 |
+
All data generation, training, and evaluation pipelines are available on [Github](https://github.com/MaxLSB/LeCarnet).
|
12 |
+
|
13 |
---
|
14 |
+
# Example Code
|
15 |
+
|
16 |
+
```
|
17 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
18 |
+
|
19 |
+
model = AutoModelForCausalLM.from_pretrained("MaxLSB/LeCarnet-8M")
|
20 |
+
tokenizer = AutoTokenizer.from_pretrained("MaxLSB/LeCarnet-8M")
|
21 |
+
|
22 |
+
prompt = "Il était une fois"
|
23 |
+
input_ids = tokenizer(prompt, return_tensors="pt").input_ids
|
24 |
+
|
25 |
+
output = model.generate(input_ids, max_length=512)
|
26 |
+
print(tokenizer.decode(output[0], skip_special_tokens=True))
|
27 |
+
```
|