Update README.md

README.md

@@ -42,42 +42,50 @@ library_name: transformers
 ---
 
 <p align="center">
-  <img src="humanflow_logofinal.png" width="340"/>
+  <img src="assets/humanflow_logofinal.png" width="340"/>
 </p>
 
 <h1 align="center">HumanFlow-Llama3-8B</h1>
 
 <p align="center"><strong>The antidote to robotic AI text.</strong></p>
 
+<p align="center">
+Rewrite synthetic AI writing into language that feels natural, fluent, and genuinely human.
+</p>
+
 <p align="center">
 
-![License](https://img.shields.io/badge/License-Apache_2.0-black?style=flat-square)
-![Base Model](https://img.shields.io/badge/Base-Llama--3%208B-black?style=flat-square)
-![Weights](https://img.shields.io/badge/Weights-Merged-black?style=flat-square)
-![Inference](https://img.shields.io/badge/GGUF-Ready-black?style=flat-square)
-![Status](https://img.shields.io/badge/Release-Stable-black?style=flat-square)
+![License](https://img.shields.io/badge/License-Apache%202.0-black?style=for-the-badge)
+![Base](https://img.shields.io/badge/Base-Llama--3%208B-black?style=for-the-badge)
+![Weights](https://img.shields.io/badge/Weights-Merged-black?style=for-the-badge)
+![Ready](https://img.shields.io/badge/GGUF-Ready-black?style=for-the-badge)
 
 </p>
 
 ---
 
-## Human Writing, Restored.
+## Why HumanFlow Exists
 
-Most AI-generated writing is easy to recognize.
+Most AI-generated writing is easy to spot.
 
-It often sounds predictable, overly polished, repetitive, structurally rigid, and emotionally flat. Whether used for articles, emails, social posts, or product copy, synthetic writing reduces trust and weakens engagement.
+It often sounds stiff, repetitive, emotionally flat, and structurally predictable. That hurts trust, lowers engagement, and makes content feel artificial.
 
-**HumanFlow-Llama3-8B** was built to solve that problem.
+**HumanFlow-Llama3-8B** was built to solve this problem.
 
-HumanFlow transforms robotic AI text into language that feels natural, fluid, readable, and genuinely human—while preserving the original meaning. It is optimized for high-quality rewriting, stylistic naturalization, and believable human tone.
+It transforms robotic AI text into writing that reads naturally, flows smoothly, and sounds human—while preserving the original meaning.
 
 ---
 
 ## Quick Stats
 
-| | | | | |
-|---|---|---|---|---|
-| **99% Human Score** | **Llama-3 8B** | **Merged Weights** | **GGUF Ready** | **Open Source** |
+| Metric | Value |
+|---|---|
+| Human-like Score | 99% |
+| Base Model | Llama-3 8B |
+| Fine-Tuning | Unsloth + LoRA |
+| Release Type | Fully Merged Weights |
+| Quantization | GGUF Ready |
+| License | Apache-2.0 |
 
 ---
 
@@ -86,68 +94,64 @@ HumanFlow transforms robotic AI text into language that feels natural, fluid, re
 | Category | Value |
 |---|---|
 | Model Name | HumanFlow-Llama3-8B |
-| Base Model | Meta Llama-3 8B Instruct |
-| Architecture | Decoder-only Transformer |
-| Fine-Tuning Method | LoRA + Full Merge |
-| Training Framework | Unsloth |
-| Primary Task | AI Text Humanization / Rewriting |
-| Input Type | Prompt + Source Text |
-| Output Type | Natural Human-like Rewrite |
-| Inference Support | Transformers, GGUF, Ollama-ready workflows |
-| License | Apache-2.0 |
+| Architecture | Transformer Decoder |
+| Base Checkpoint | Meta-Llama-3-8B-Instruct |
+| Training Method | Supervised Fine-Tuning |
+| Adapter Method | LoRA |
+| Merge Status | Fully Merged |
+| Primary Use | AI Text Humanization |
+| Inference | Transformers / vLLM / GGUF |
 
 ---
 
 ## Before vs After
 
-## Example 1 — Marketing Copy
+### Example 1 — Marketing Copy
 
-**Input (Robotic)**  
-Our platform provides users with innovative solutions that enhance productivity and maximize efficiency.
+**Input**  
+Our platform provides innovative solutions that maximize productivity and efficiency.
 
-**Output (HumanFlow)**  
-Our platform helps people get more done with smarter tools that make work faster, easier, and less stressful.
+**Output**  
+Our platform helps people work faster and smarter with tools that make everyday tasks easier.
 
 ---
 
-## Example 2 — Student Writing
+### Example 2 — Student Writing
 
-**Input (Robotic)**  
-Climate change is a significant issue that requires immediate global attention and cooperative action.
+**Input**  
+Climate change is a significant issue requiring immediate international cooperation.
 
-**Output (HumanFlow)**  
-Climate change is one of the biggest challenges we face today, and solving it will require countries to act together now.
+**Output**  
+Climate change is a serious global challenge, and solving it will require countries to act together now.
 
 ---
 
-## Example 3 — Email Rewrite
+### Example 3 — Email Rewrite
 
-**Input (Robotic)**  
-I am writing this email to inform you that the requested file has been attached for your review.
+**Input**  
+I am writing this email to inform you that the requested document has been attached.
 
-**Output (HumanFlow)**  
-Just wanted to let you know I’ve attached the file for your review.
+**Output**  
+Just letting you know I’ve attached the document you requested.
 
 ---
 
-## Built For Real Work
-
-HumanFlow is designed for teams and builders who need natural writing at scale.
+## Built For
 
-- **SEO agencies** improving readability and reducing AI tone  
-- **Content teams** polishing drafts before publishing  
-- **Students** making essays sound more natural  
-- **Developers** integrating rewrite pipelines into apps  
-- **Founders** improving landing pages and outreach copy  
-- **Chatbots** generating warmer, more believable responses  
-- **Email workflows** reducing template stiffness  
-- **Social media teams** creating more human voice content  
+- SEO agencies improving readability  
+- Content teams polishing drafts  
+- Students improving natural tone  
+- Developers integrating rewrite pipelines  
+- Startup founders refining copy  
+- Chatbots with better responses  
+- Email automation workflows  
+- Social media content teams  
 
 ---
 
 ## Evaluation
 
-Automated evaluation results measured at **temperature = 0.7**
+Automated benchmark results measured at **temperature = 0.7**
 
 | Metric | Value | Interpretation |
 |--------|-------|----------------|
@@ -156,7 +160,7 @@ Automated evaluation results measured at **temperature = 0.7**
 | Perplexity | 1.5242 | High fluency and coherence |
 | Text Overlap | 0.0528 | Minimal lexical copying |
 
-These scores indicate that HumanFlow preserves meaning while actively regenerating phrasing into more natural language.
+These results indicate HumanFlow preserves meaning while actively regenerating more natural phrasing.
 
 ---
 
@@ -166,7 +170,7 @@ These scores indicate that HumanFlow preserves meaning while actively regenerati
 from transformers import AutoTokenizer, AutoModelForCausalLM
 import torch
 
-model_id = "your-username/HumanFlow-Llama3-8B"
+model_id = "randhir302/HumanFlow-Llama3-8B"
 
 tokenizer = AutoTokenizer.from_pretrained(model_id)
 model = AutoModelForCausalLM.from_pretrained(
@@ -176,9 +180,8 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 
 prompt = """
-Rewrite the following text so it sounds natural, fluent, and human:
+Rewrite this text naturally:
 
-Text:
 The company offers innovative solutions that optimize workflow efficiency.
 """
 
@@ -191,4 +194,4 @@ outputs = model.generate(
     top_p=0.9
 )
 
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))