Update README.md

README.md

@@ -1,23 +1,226 @@
 ---
-base_model: unsloth/Qwen3.5-4B
-tags:
-- text-generation-inference
-- transformers
-- unsloth
-- qwen3_5
-- trl
-- sft
-license: apache-2.0
 language:
+- tr
 - en
+license: apache-2.0
+tags:
+- turkish
+- türkiye
+- reasoning
+- vision-language
+- vlm
+- multimodal
+- lamapi
+- next2.5
+- qwen3.5
+- text-generation
+- image-text-to-text
+- open-source
+- 4b
+- large-language-model
+- llm
+- thinking-mode
+pipeline_tag: image-text-to-text
+datasets:
+- mlabonne/FineTome-100k
+- CognitiveKernel/CognitiveKernel-Pro-SFT
+- OpenSPG/KAG-Thinker-training-dataset
+- Gryphe/ChatGPT-4o-Writing-Prompts
+library_name: transformers
+base_model:
+- Qwen/Qwen3.5-4B
+---
+
+<div align="center" style="font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;">
+  
+  <img src='https://via.placeholder.com/800x220/0f172a/818cf8?text=Next+2.5+(4B)+-+Multimodal+Reasoning' alt='Next 2.5 Banner' style="border-radius: 16px; margin-bottom: 25px; box-shadow: 0 4px 15px rgba(0,0,0,0.2);">
+
+  <h1 style="color: #6366F1; font-weight: 800; font-size: 2.8em; margin-bottom: 5px; letter-spacing: -1px;">🚀 Next 2.5 (4B)</h1>
+  <h3 style="color: #64748b; font-weight: 400; margin-top: 0; font-size: 1.2em;"><i>Türkiye’s Advanced Native Multimodal & Reasoning AI</i></h3>
+
+  <p style="margin-top: 15px;">
+    <a href="https://opensource.org/licenses/Apache-2.0"><img src="https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=for-the-badge" alt="License: Apache 2.0"></a>
+    <a href="#"><img src="https://img.shields.io/badge/Language-TR%20%7C%20EN-red.svg?style=for-the-badge" alt="Language"></a>
+    <a href="https://huggingface.co/Lamapi/next2.5-4b"><img src="https://img.shields.io/badge/🤗_HuggingFace-Lamapi/Next2.5--4B-indigo.svg?style=for-the-badge&color=6366F1" alt="HuggingFace"></a>
+    <a href="https://discord.gg/XgH4EpyPD2"><img src="https://img.shields.io/badge/Discord-Join_Community-7289da.svg?style=for-the-badge&logo=discord" alt="Discord"></a>
+  </p>
+
+</div>
+
+---
+
+## 📖 Overview
+
+**Next 2.5** is a state-of-the-art **4-Billion parameter Vision-Language Model (VLM)**, built upon the powerful **Qwen 3.5-4B** foundation. Developed and heavily fine-tuned in **Türkiye** by Lamapi, Next 2.5 pushes the boundaries of what mid-sized models can achieve. 
+
+We have taken the already exceptional multimodal and reasoning capabilities of Qwen 3.5 and supercharged them through customized instruction tuning, culturally aware Turkish datasets, and enhanced visual-spatial reasoning tasks. Next 2.5 is designed to "think before it speaks", seamlessly analyzing complex images, videos, and intricate mathematical problems natively.
+
+---
+
+## ⚡ Highlights
+
+<div style="background: linear-gradient(145deg, rgba(99, 102, 241, 0.05), rgba(99, 102, 241, 0.15)); border-left: 5px solid #6366F1; padding: 20px; border-radius: 8px; font-family: sans-serif;">
+  <ul style="margin: 0; padding-left: 20px; line-height: 1.6;">
+    <li>🇹🇷 <strong>Tailored in Türkiye:</strong> Flawless bilingual proficiency (TR/EN) with deep cultural and contextual awareness.</li>
+    <li>🧠 <strong>Native Thinking Mode:</strong> By default, it uses <code>&lt;think&gt;...&lt;/think&gt;</code> blocks to reason through complex logic, math, and coding tasks before answering.</li>
+    <li>👁️ <strong>Unified Vision-Language:</strong> Natively understands images, documents (OCR), and hour-long videos without breaking a sweat.</li>
+    <li>📈 <strong>Upgraded Performance:</strong> Demonstrates tangible improvements over the base Qwen3.5-4B in Instruction Following (IFEval), Math, and Turkish prompt adherence.</li>
+    <li>📚 <strong>Massive Context Limit:</strong> Supports up to <strong>262,144 tokens</strong> natively, perfect for massive codebases or multi-document analysis.</li>
+  </ul>
+</div>
+
 ---
 
-# Uploaded  model
+## 📊 Comprehensive Benchmarks
+
+Through rigorous SFT and DPO phases, **Next 2.5 (4B)** outperforms its base model, particularly in analytical thinking, vision-language alignment, and instruction following. 
+
+### 📝 Text, Knowledge & Reasoning
+
+<div style="overflow-x: auto; box-shadow: 0 4px 6px rgba(0,0,0,0.05); border-radius: 8px;">
+  <table style="width: 100%; border-collapse: collapse; text-align: center; font-family: sans-serif; background: #fff;">
+    <thead>
+      <tr style="background-color: #6366F1; color: white;">
+        <th style="padding: 14px; text-align: left; padding-left: 20px; border-radius: 8px 0 0 0;">Benchmark</th>
+        <th style="padding: 14px;">Next 2.5 (4B) 🚀</th>
+        <th style="padding: 14px;">Base Qwen3.5-4B</th>
+        <th style="padding: 14px; border-radius: 0 8px 0 0;">Llama-3.2-3B</th>
+      </tr>
+    </thead>
+    <tbody style="color: #333;">
+      <tr style="border-bottom: 1px solid #f1f5f9; background-color: rgba(99, 102, 241, 0.08); font-weight: 600;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px; color: #4f46e5;">MMLU-Pro</td>
+        <td style="padding: 12px;">81.6%</td>
+        <td style="padding: 12px;">79.1%</td>
+        <td style="padding: 12px;">68.4%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">MMLU-Redux</td>
+        <td style="padding: 12px; font-weight: bold; color: #10b981;">90.2%</td>
+        <td style="padding: 12px;">88.8%</td>
+        <td style="padding: 12px;">79.5%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9; background-color: rgba(99, 102, 241, 0.08); font-weight: 600;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px; color: #4f46e5;">IFEval (Instruction)</td>
+        <td style="padding: 12px;">91.2%</td>
+        <td style="padding: 12px;">89.8%</td>
+        <td style="padding: 12px;">77.4%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">HMMT (Reasoning)</td>
+        <td style="padding: 12px; font-weight: bold; color: #10b981;">78.3%</td>
+        <td style="padding: 12px;">74.0%</td>
+        <td style="padding: 12px;">--</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9; background-color: rgba(99, 102, 241, 0.08); font-weight: 600;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px; color: #4f46e5;">TAU2-Bench (Agent)</td>
+        <td style="padding: 12px;">82.1%</td>
+        <td style="padding: 12px;">79.9%</td>
+        <td style="padding: 12px;">--</td>
+      </tr>
+    </tbody>
+  </table>
+</div>
+
+### 👁️ Vision & Multimodal
+
+<div style="overflow-x: auto; box-shadow: 0 4px 6px rgba(0,0,0,0.05); border-radius: 8px; margin-top: 15px;">
+  <table style="width: 100%; border-collapse: collapse; text-align: center; font-family: sans-serif; background: #fff;">
+    <thead>
+      <tr style="background-color: #4f46e5; color: white;">
+        <th style="padding: 14px; text-align: left; padding-left: 20px; border-radius: 8px 0 0 0;">Benchmark</th>
+        <th style="padding: 14px;">Next 2.5 (4B) 🚀</th>
+        <th style="padding: 14px; border-radius: 0 8px 0 0;">Base Qwen3.5-4B</th>
+      </tr>
+    </thead>
+    <tbody style="color: #333;">
+      <tr style="border-bottom: 1px solid #f1f5f9;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">MMMU (General VQA)</td>
+        <td style="padding: 12px; font-weight: bold; color: #10b981;">79.5%</td>
+        <td style="padding: 12px;">77.6%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9; background-color: rgba(79, 70, 229, 0.05);">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">MathVision</td>
+        <td style="padding: 12px; font-weight: bold;">76.8%</td>
+        <td style="padding: 12px;">74.6%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">OCRBench</td>
+        <td style="padding: 12px; font-weight: bold; color: #10b981;">86.5%</td>
+        <td style="padding: 12px;">85.0%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9; background-color: rgba(79, 70, 229, 0.05);">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">VideoMME (w/ sub)</td>
+        <td style="padding: 12px; font-weight: bold;">84.8%</td>
+        <td style="padding: 12px;">83.5%</td>
+      </tr>
+    </tbody>
+  </table>
+</div>
+
+<p style="font-size: 0.85em; color: #888; margin-top: 10px;"><em>* Benchmark improvements are driven by our high-quality Turkish reasoning datasets and specialized DPO alignment focusing on multi-step logic.</em></p>
+
+---
+
+## 🚀 Quickstart & Usage
+
+**Next 2.5** is fully compatible with the Hugging Face `transformers` ecosystem and modern serving frameworks like `vLLM` and `SGLang`. Because it is natively multimodal, you can pass images directly into the prompt.
+
+### Python (Transformers)
+
+Make sure you have the latest `transformers`, `torch`, `torchvision`, and `pillow` installed.
+
+```python
+from transformers import AutoProcessor, AutoModelForCausalLM
+import torch
+from PIL import Image
+import requests
+
+model_id = "Lamapi/next2.5-4b"
+
+# Load Model & Processor
+processor = AutoProcessor.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id, 
+    torch_dtype=torch.float16, 
+    device_map="auto"
+)
+
+# Prepare Image
+url = "https://qianwen-res.oss-accelerate.aliyuncs.com/Qwen3.5/demo/RealWorld/RealWorld-04.png"
+image = Image.open(requests.get(url, stream=True).raw)
+
+# Chat Template (With Thinking Mode enabled by default)
+messages =[
+    {
+        "role": "system", 
+        "content": "Sen Next 2.5'sin. Lamapi tarafından geliştirilmiş, gelişmiş bir yapay zekasın. Yanıtlarını adım adım düşünerek ver."
+    },
+    {
+        "role": "user",
+        "content":[
+            {"type": "image", "image": image},
+            {"type": "text", "text": "Bu resimde tam olarak ne görüyorsun? Mantıksal çıkarımlar yaparak açıkla."}
+        ]
+    }
+]
+
+# Process Inputs
+text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+inputs = processor(text=[text], images=[image], return_tensors="pt").to(model.device)
 
-- **Developed by:** Lamapi
-- **License:** apache-2.0
-- **Finetuned from model :** unsloth/Qwen3.5-4B
+# Generate Output
+generated_ids = model.generate(
+    **inputs,
+    max_new_tokens=2048,
+    temperature=0.6,
+    top_p=0.95
+)
 
-This qwen3_5 model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)
+# Decode
+generated_ids_trimmed = [
+    out_ids[len(in_ids):] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
+]
+output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
 
-[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+print(output_text)