Downloads · 30 days
0
ProphetNet-Large-Story-Generation
harsharajkumar273/ProphetNet-Large-Story-Generation
ProphetNet-Large-Story-Generation is a text generation model from harsharajkumar273. Use it when you need the model to write or continue text. It is set up for peft. The card lists the license as apache-2.0.
A fine-tuned model for transforming research paper summaries into engaging short stories. This is the second stage of a two-step Research Paper Simplifier pipeline, built on top of harsharajkumar273/ProphetNet-Large-S…
Access
Public
Updated Apr 2, 2026
Repo size
—
Likes
0
Public
Repo makeup
Click a slice to open those files.
.tokenizer232 KB · 98%
At a glance
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Access
- Public
- Created
- Apr 2, 2026
- Updated
- Apr 2, 2026
- SHA
- 9966e250
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
ProphetNet-Large-Story-Generation
A fine-tuned model for transforming research paper summaries into engaging short stories. This is the second stage of a two-step Research Paper Simplifier pipeline, built on top of harsharajkumar273/ProphetNet-Large-Summarization.
Model Description
This model takes a summary of a research paper and generates an immersive, narrative-style short story. Fine-tuned using LoRA (PEFT) with 4-bit quantization.
Pipeline
Research Paper ──► [ProphetNet-Large-Summarization] ──► Summary ──► [ProphetNet-Large-Story-Generation] ──► Story
Training Details
| Parameter | Value |
|---|---|
| Base model | harsharajkumar273/ProphetNet-Large-Summarization |
| Task | Story Generation |
| Max input length | 1024 tokens |
| Max target length | 512 tokens |
| Learning rate | 5e-5 |
| Batch size | 2 |
| Gradient accumulation steps | 4 |
| Warmup steps | 1000 |
| Weight decay | 0.01 |
| Fine-tuning method | LoRA (r=16, alpha=64, targets: query_proj, value_proj) |
| Quantization | 4-bit NF4 (bitsandbytes) |
Usage
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
# Stage 1: Summarize the paper
sum_tokenizer = AutoTokenizer.from_pretrained("harsharajkumar273/ProphetNet-Large-Summarization")
sum_model = AutoModelForSeq2SeqLM.from_pretrained("harsharajkumar273/ProphetNet-Large-Summarization")
paper_text = "Your research paper text here..."
word_count = len(paper_text.split())
sum_prompt = f"Summarize this part of the research paper to less than {word_count // 10} words:\n{paper_text}"
sum_inputs = sum_tokenizer(sum_prompt, return_tensors="pt", max_length=2048, truncation=True)
sum_outputs = sum_model.generate(**sum_inputs, max_length=256, num_beams=4)
summary = sum_tokenizer.decode(sum_outputs[0], skip_special_tokens=True)
# Stage 2: Generate a story from the summary
story_tokenizer = AutoTokenizer.from_pretrained("harsharajkumar273/ProphetNet-Large-Story-Generation")
story_model = AutoModelForSeq2SeqLM.from_pretrained("harsharajkumar273/ProphetNet-Large-Story-Generation")
story_inputs = story_tokenizer(summary, return_tensors="pt", max_length=1024, truncation=True)
story_outputs = story_model.generate(**story_inputs, max_length=512, num_beams=4)
story = story_tokenizer.decode(story_outputs[0], skip_special_tokens=True)
print(story)
Evaluation Metrics
Evaluated using BERTScore and SBERTScore on a held-out 10% test split.
Related Models
- Task
- Text Generation
- Library
- peft
- License
- apache-2.0
- Languages
- en
- Created
- Apr 2, 2026
- Updated
- Apr 2, 2026