Update README
Browse files
README.md
CHANGED
@@ -9,25 +9,79 @@ model-index:
|
|
9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
should probably proofread and complete it, then remove this comment. -->
|
11 |
|
12 |
-
#
|
|
|
|
|
|
|
13 |
|
14 |
-
This model is a fine-tuned version of [Tincando/fiction_story_generator](https://huggingface.co/Tincando/fiction_story_generator) on an unknown dataset.
|
15 |
-
It achieves the following results on the evaluation set:
|
16 |
-
- Loss: 3.1357
|
17 |
|
18 |
## Model description
|
19 |
|
20 |
-
|
|
|
|
|
21 |
|
22 |
## Intended uses & limitations
|
23 |
|
24 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
25 |
|
26 |
-
|
|
|
|
|
|
|
27 |
|
28 |
-
|
|
|
29 |
|
30 |
-
|
|
|
|
|
31 |
|
32 |
### Training hyperparameters
|
33 |
|
|
|
9 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
10 |
should probably proofread and complete it, then remove this comment. -->
|
11 |
|
12 |
+
# GPT-Neo for Fiction Story Generation
|
13 |
+
|
14 |
+
This model is a fine-tuned version of EleutherAI's GPT-Neo-125M model, optimized for generating fiction stories.
|
15 |
+
It has been trained on the dataset available at https://github.com/facebookresearch/fairseq/tree/main/examples/stories.
|
16 |
|
|
|
|
|
|
|
17 |
|
18 |
## Model description
|
19 |
|
20 |
+
- Model Name: GPT-Neo-Fiction
|
21 |
+
- Fine-Tuned By: [Tin/Tincando, Darko Etinger]
|
22 |
+
- Model Version: 1.0
|
23 |
|
24 |
## Intended uses & limitations
|
25 |
|
26 |
+
The model is designed for creative fiction story generation. It can be used for various purposes, including but not limited to:
|
27 |
+
|
28 |
+
- Storytelling: Generate engaging and imaginative fiction stories.
|
29 |
+
- Content Generation: Create content for blogs, websites, or other media with a storytelling element.
|
30 |
+
- Creative Writing: Assist authors and writers in brainstorming ideas and expanding narratives.
|
31 |
+
|
32 |
+
## Model Performance
|
33 |
+
|
34 |
+
- Training Data: The model was trained on a diverse dataset of fiction stories.
|
35 |
+
- Evaluation Metrics: Performance metrics, such as perplexity or BLEU scores, may vary depending on the specific task and dataset.
|
36 |
+
|
37 |
+
## Limitations
|
38 |
+
|
39 |
+
- Content Quality: While GPT-Neo-Fiction can generate creative stories, the quality and coherence of the output may vary, and it may occasionally produce nonsensical or inappropriate content.
|
40 |
+
- Bias: The model may exhibit biases present in the training data, and it is essential to be cautious when using it for sensitive topics or content.
|
41 |
+
- Length of Output: The model may generate text with variable length, and it may not always produce the desired length of output.
|
42 |
+
- Fine-Tuning Data: The quality of generated stories is dependent on the quality and diversity of the fine-tuning dataset.
|
43 |
+
|
44 |
+
## Usage
|
45 |
+
|
46 |
+
```
|
47 |
+
from transformers import GPTNeoForCausalLM, GPT2Tokenizer
|
48 |
+
|
49 |
+
tokenizer = GPT2Tokenizer.from_pretrained(Tincando/fiction_story_generator)
|
50 |
+
model = GPTNeoForCausalLM.from_pretrained(Tincando/fiction_story_generator)
|
51 |
+
|
52 |
+
# Generate a fiction story
|
53 |
+
input_prompt = "[WP] I can't believe I died the same way twice."
|
54 |
+
input_ids = tokenizer(input_prompt, add_special_tokens=False, return_tensors="pt").input_ids
|
55 |
+
|
56 |
+
output = model.generate(input_ids,
|
57 |
+
max_length=300,
|
58 |
+
temperature=0.9,
|
59 |
+
top_k=2,
|
60 |
+
top_p=0.9,
|
61 |
+
repetition_penalty=1.2,
|
62 |
+
do_sample=True,
|
63 |
+
num_return_sequences=2
|
64 |
+
)
|
65 |
+
|
66 |
+
generated_story = tokenizer.batch_decode(output,clean_up_tokenization_spaces=True)[0]
|
67 |
+
print(generated_story)
|
68 |
+
```
|
69 |
+
|
70 |
+
## Ethical Considerations
|
71 |
+
|
72 |
+
When using this model, consider the following ethical guidelines:
|
73 |
|
74 |
+
- Content Moderation: Implement content moderation to ensure that the generated stories do not violate guidelines or community standards.
|
75 |
+
- Bias and Fairness: Be aware of potential biases in the model's output and take steps to mitigate them.
|
76 |
+
- Privacy: Avoid using personal or sensitive information as input prompts.
|
77 |
+
- Legal Compliance: Ensure that the generated content complies with copyright and intellectual property laws.
|
78 |
|
79 |
+
##Citation
|
80 |
+
If you use GPT-Neo-Fiction in your work, please consider citing the original GPT-Neo model and the dataset used for fine-tuning:
|
81 |
|
82 |
+
- [GPT-Neo Paper](https://github.com/EleutherAI/gpt-neo)
|
83 |
+
- [Fairseq Repository](https://github.com/facebookresearch/fairseq/tree/main/examples/stories)
|
84 |
+
- [Hierarchical Neural Story Generation](https://arxiv.org/abs/1805.04833)
|
85 |
|
86 |
### Training hyperparameters
|
87 |
|