201 lines
3.9 KiB
Markdown
201 lines
3.9 KiB
Markdown
|
|
---
|
|||
|
|
language:
|
|||
|
|
- en
|
|||
|
|
license: apache-2.0
|
|||
|
|
base_model: unsloth/llama-3-8b-Instruct-bnb-4bit
|
|||
|
|
library_name: transformers
|
|||
|
|
pipeline_tag: text-generation
|
|||
|
|
|
|||
|
|
tags:
|
|||
|
|
- text-generation
|
|||
|
|
- llama3
|
|||
|
|
- humanizer
|
|||
|
|
- rewriting
|
|||
|
|
- conversational
|
|||
|
|
- merged
|
|||
|
|
- sft
|
|||
|
|
- editorial
|
|||
|
|
|
|||
|
|
widget:
|
|||
|
|
- text: "Rewrite this in a more human tone: The system is functioning correctly."
|
|||
|
|
example_title: "Smooth System"
|
|||
|
|
|
|||
|
|
- text: "Rewrite this in a more human tone: The implementation has been completed successfully."
|
|||
|
|
example_title: "Successful Setup"
|
|||
|
|
|
|||
|
|
- text: "Rewrite this in a more human tone: The user is advised to proceed with caution."
|
|||
|
|
example_title: "Friendly Warning"
|
|||
|
|
|
|||
|
|
model-index:
|
|||
|
|
- name: HumanFlow-Llama3-8B
|
|||
|
|
results:
|
|||
|
|
- task:
|
|||
|
|
type: text-generation
|
|||
|
|
dataset:
|
|||
|
|
name: Internal Evaluation Suite
|
|||
|
|
type: custom
|
|||
|
|
metrics:
|
|||
|
|
- type: BERTScore F1
|
|||
|
|
value: 0.8424
|
|||
|
|
- type: ROUGE-L
|
|||
|
|
value: 0.0908
|
|||
|
|
- type: Perplexity
|
|||
|
|
value: 1.5242
|
|||
|
|
- type: Text Overlap
|
|||
|
|
value: 0.0528
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
<p align="center">
|
|||
|
|
<img src="https://huggingface.co/randhir302/HumanFlow/resolve/main/humanflow_logofinal.png" width="240" height="240">
|
|||
|
|
</p>
|
|||
|
|
|
|||
|
|
# HumanFlow-Llama3-8B
|
|||
|
|
|
|||
|
|
### Humanize AI Text with Natural Structure, Flow & Tone
|
|||
|
|
|
|||
|
|
[🤗 Hugging Face Model](https://huggingface.co/randhir302/HumanFlow) •
|
|||
|
|
[💻 GitHub Repository](https://github.com/iamhero2709/HumanFlow) •
|
|||
|
|
Apache-2.0 License
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Overview
|
|||
|
|
|
|||
|
|
HumanFlow-Llama3-8B is a fine-tuned Llama 3 model designed to transform robotic AI-generated writing into content that feels natural, human, readable, and authentic.
|
|||
|
|
|
|||
|
|
Instead of replacing words only, HumanFlow improves:
|
|||
|
|
|
|||
|
|
- sentence rhythm
|
|||
|
|
- structure
|
|||
|
|
- tone
|
|||
|
|
- flow
|
|||
|
|
- readability
|
|||
|
|
- realism
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Why HumanFlow?
|
|||
|
|
|
|||
|
|
Most AI-generated text feels:
|
|||
|
|
|
|||
|
|
- repetitive
|
|||
|
|
- over-polished
|
|||
|
|
- generic
|
|||
|
|
- predictable
|
|||
|
|
- emotionally flat
|
|||
|
|
|
|||
|
|
HumanFlow rewrites outputs to feel more organic and naturally written.
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Performance Snapshot
|
|||
|
|
|
|||
|
|
| Metric | Base Model | HumanFlow |
|
|||
|
|
|--------|-----------|----------|
|
|||
|
|
| Human-Like Score | 18% | **99%** |
|
|||
|
|
| Natural Tone | Low | **High** |
|
|||
|
|
| Rewrite Quality | Basic | **Advanced** |
|
|||
|
|
| Readability | Generic | **Strong** |
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Internal Evaluation
|
|||
|
|
|
|||
|
|
| Metric | Score |
|
|||
|
|
|--------|------|
|
|||
|
|
| BERTScore F1 | **0.8424** |
|
|||
|
|
| ROUGE-L | **0.0908** |
|
|||
|
|
| Perplexity | **1.5242** |
|
|||
|
|
| Text Overlap | **0.0528** |
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Best Use Cases
|
|||
|
|
|
|||
|
|
- SEO rewriting
|
|||
|
|
- Blog enhancement
|
|||
|
|
- Student writing cleanup
|
|||
|
|
- Email personalization
|
|||
|
|
- AI content polishing
|
|||
|
|
- SaaS integrations
|
|||
|
|
- Human-style generation pipelines
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Before vs After
|
|||
|
|
|
|||
|
|
### Input
|
|||
|
|
|
|||
|
|
> In today’s rapidly evolving digital landscape, it is imperative for organizations to leverage strategic methodologies in order to maximize engagement.
|
|||
|
|
|
|||
|
|
### HumanFlow Output
|
|||
|
|
|
|||
|
|
> Online markets move fast. If a company wants attention, it needs smart strategy, clear messaging, and content people actually care about.
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Quickstart
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
|||
|
|
import torch
|
|||
|
|
|
|||
|
|
model_id = "randhir302/HumanFlow"
|
|||
|
|
|
|||
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id)
|
|||
|
|
|
|||
|
|
model = AutoModelForCausalLM.from_pretrained(
|
|||
|
|
model_id,
|
|||
|
|
torch_dtype=torch.float16,
|
|||
|
|
device_map="auto"
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
prompt = """
|
|||
|
|
Rewrite this in a more human tone:
|
|||
|
|
|
|||
|
|
Artificial intelligence is transforming industries worldwide.
|
|||
|
|
"""
|
|||
|
|
|
|||
|
|
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
|||
|
|
|
|||
|
|
outputs = model.generate(
|
|||
|
|
**inputs,
|
|||
|
|
max_new_tokens=220,
|
|||
|
|
temperature=0.75,
|
|||
|
|
top_p=0.90,
|
|||
|
|
repetition_penalty=1.10
|
|||
|
|
)
|
|||
|
|
|
|||
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True))
|
|||
|
|
|
|||
|
|
```
|
|||
|
|
## Recommended Settings
|
|||
|
|
|
|||
|
|
```python
|
|||
|
|
temperature = 0.75
|
|||
|
|
top_p = 0.90
|
|||
|
|
repetition_penalty = 1.10
|
|||
|
|
max_new_tokens = 700
|
|||
|
|
|
|||
|
|
## Roadmap
|
|||
|
|
|
|||
|
|
- [x] Public Launch
|
|||
|
|
- [x] Hugging Face Release
|
|||
|
|
- [x] Fine-Tuned Base Model
|
|||
|
|
- [ ] GGUF Quantized Release
|
|||
|
|
- [ ] HumanFlow Pro API
|
|||
|
|
- [ ] Browser Editor
|
|||
|
|
- [ ] Multilingual Version
|
|||
|
|
|
|||
|
|
---
|
|||
|
|
|
|||
|
|
## Community
|
|||
|
|
|
|||
|
|
If HumanFlow helps you:
|
|||
|
|
|
|||
|
|
⭐ Like the model
|
|||
|
|
⭐ Share outputs
|
|||
|
|
⭐ Benchmark it
|
|||
|
|
⭐ Build products with it
|
|||
|
|
|