Update README.md
Browse files
README.md
CHANGED
@@ -7,6 +7,10 @@ tags:
|
|
7 |
model-index:
|
8 |
- name: gpt-neo-125m-finetuned-shakespeare
|
9 |
results: []
|
|
|
|
|
|
|
|
|
10 |
---
|
11 |
|
12 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
@@ -18,17 +22,23 @@ This model is a fine-tuned version of [EleutherAI/gpt-neo-125m](https://huggingf
|
|
18 |
It achieves the following results on the evaluation set:
|
19 |
- Loss: 4.1126
|
20 |
|
21 |
-
##
|
22 |
|
23 |
-
|
24 |
|
25 |
-
|
|
|
26 |
|
27 |
-
|
|
|
|
|
|
|
|
|
|
|
28 |
|
29 |
## Training and evaluation data
|
30 |
|
31 |
-
|
32 |
|
33 |
## Training procedure
|
34 |
|
@@ -57,4 +67,4 @@ The following hyperparameters were used during training:
|
|
57 |
- Transformers 4.48.3
|
58 |
- Pytorch 2.5.1+cu124
|
59 |
- Datasets 3.3.2
|
60 |
-
- Tokenizers 0.21.0
|
|
|
7 |
model-index:
|
8 |
- name: gpt-neo-125m-finetuned-shakespeare
|
9 |
results: []
|
10 |
+
datasets:
|
11 |
+
- 2nji/Shakespeare_Corpus
|
12 |
+
language:
|
13 |
+
- en
|
14 |
---
|
15 |
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
|
|
22 |
It achieves the following results on the evaluation set:
|
23 |
- Loss: 4.1126
|
24 |
|
25 |
+
## How to use
|
26 |
|
27 |
+
You can use this model directly with a pipeline for text generation. This example generates a different sequence each time it's run:
|
28 |
|
29 |
+
```python
|
30 |
+
from transformers import pipeline
|
31 |
|
32 |
+
generator = pipeline('text-generation', model='2nji/gpt-neo-125m-finetuned-shakespeare')
|
33 |
+
|
34 |
+
generator("And all that", do_sample=True, min_length=20)
|
35 |
+
|
36 |
+
# [{'generated_text': "And all that in heaven is free: Thou bestow'd on God, so to my house, and in the"}]
|
37 |
+
```
|
38 |
|
39 |
## Training and evaluation data
|
40 |
|
41 |
+
This model was finetuned using the the [Shakespare_corpus](https://huggingface.co/datasets/2nji/Shakespeare_Corpus) Dataset
|
42 |
|
43 |
## Training procedure
|
44 |
|
|
|
67 |
- Transformers 4.48.3
|
68 |
- Pytorch 2.5.1+cu124
|
69 |
- Datasets 3.3.2
|
70 |
+
- Tokenizers 0.21.0
|