Update README.md

README.md

@@ -1,3 +1,308 @@
----
-license: apache-2.0
----
+---
+language:
+- tr
+- en
+- de
+- es
+- fr
+- ru
+- zh
+- ja
+- ko
+license: apache-2.0
+tags:
+- turkish
+- türkiye
+- reasoning
+- vision-language
+- vlm
+- multimodal
+- lamapi
+- next2.5
+- qwen3.5
+- gemma-3
+- text-generation
+- image-text-to-text
+- open-source
+- 4b
+- edge-ai
+- 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:
+- thelamapi/next2.5
+---
+
+<div align="center" style="font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;">
+    
+
+  ![next2ultra](https://cdn-uploads.huggingface.co/production/uploads/67d46bc5fe6ad6f6511d6f44/nkLUtS6XkY02YMfiSASTu.png)
+
+  <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://cdn-uploads.huggingface.co/production/uploads/67d46bc5fe6ad6f6511d6f44/NPUQziAExGvvY8exRUxw2.png" 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 in 2026. 
+
+We have taken the already exceptional multimodal and reasoning capabilities of the base model 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>Class-Leading Performance:</strong> Outperforms heavyweights in its parameter class (Gemma-3-4B, Phi-4-Mini) and even rivals closed-source edge models like GPT-5-Nano.</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>
+
+---
+
+## 📊 Comprehensive Benchmarks
+
+Through rigorous SFT and DPO phases, **Next 2.5 (4B)** sets a new standard for the ~4B parameter weight class. It consistently outperforms modern edge models and punches far above its weight, rivaling 8B-11B models in vision and reasoning.
+
+### 📝 Text, Knowledge & Reasoning (Sub-5B Class)
+
+<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; min-width: 800px;">
+    <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; font-size: 1.1em;">Next 2.5 (4B) 🚀</th>
+        <th style="padding: 14px;">Qwen 3.5 (4B)</th>
+        <th style="padding: 14px;">Gemma-3 (4B)</th>
+        <th style="padding: 14px;">Phi-4-Mini (3.8B)</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; color: #10b981;">81.6%</td>
+        <td style="padding: 12px;">79.1%</td>
+        <td style="padding: 12px;">76.5%</td>
+        <td style="padding: 12px;">78.2%</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;">86.1%</td>
+        <td style="padding: 12px;">87.5%</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; color: #10b981;">91.2%</td>
+        <td style="padding: 12px;">89.8%</td>
+        <td style="padding: 12px;">85.4%</td>
+        <td style="padding: 12px;">88.1%</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;">70.2%</td>
+        <td style="padding: 12px;">72.8%</td>
+        <td style="padding: 12px; color: #94a3b8;">--</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;">LiveCodeBench v6</td>
+        <td style="padding: 12px; color: #10b981;">58.4%</td>
+        <td style="padding: 12px;">55.8%</td>
+        <td style="padding: 12px;">51.0%</td>
+        <td style="padding: 12px;">54.2%</td>
+        <td style="padding: 12px;">45.1%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">TAU2-Bench (Agent)</td>
+        <td style="padding: 12px; font-weight: bold; color: #10b981;">82.1%</td>
+        <td style="padding: 12px;">79.9%</td>
+        <td style="padding: 12px;">72.4%</td>
+        <td style="padding: 12px;">75.0%</td>
+        <td style="padding: 12px; color: #94a3b8;">--</td>
+      </tr>
+    </tbody>
+  </table>
+</div>
+
+### 👁️ Vision & Multimodal Edge
+
+Next 2.5's visual cortex allows it to rival or beat proprietary nano-models from leading labs and larger 11B parameter open-weight models.
+
+<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; min-width: 800px;">
+    <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; font-size: 1.1em;">Next 2.5 (4B) 🚀</th>
+        <th style="padding: 14px;">Qwen 3.5 (4B)</th>
+        <th style="padding: 14px;">Gemini-2.5 Flash-Lite</th>
+        <th style="padding: 14px;">GPT-5-Nano</th>
+        <th style="padding: 14px; border-radius: 0 8px 0 0;">Llama-3.2 (11B Vision)</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>
+        <td style="padding: 12px;">73.4%</td>
+        <td style="padding: 12px;">75.8%</td>
+        <td style="padding: 12px;">71.2%</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; color: #10b981;">76.8%</td>
+        <td style="padding: 12px;">74.6%</td>
+        <td style="padding: 12px;">52.1%</td>
+        <td style="padding: 12px;">62.2%</td>
+        <td style="padding: 12px;">50.5%</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>
+        <td style="padding: 12px;">82.5%</td>
+        <td style="padding: 12px;">75.3%</td>
+        <td style="padding: 12px;">74.1%</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; color: #10b981;">84.8%</td>
+        <td style="padding: 12px;">83.5%</td>
+        <td style="padding: 12px;">74.6%</td>
+        <td style="padding: 12px;">71.7%</td>
+        <td style="padding: 12px;">68.9%</td>
+      </tr>
+      <tr style="border-bottom: 1px solid #f1f5f9;">
+        <td style="padding: 12px; text-align: left; padding-left: 20px;">CountBench (Spatial)</td>
+        <td style="padding: 12px; font-weight: bold; color: #10b981;">97.5%</td>
+        <td style="padding: 12px;">96.3%</td>
+        <td style="padding: 12px;">79.2%</td>
+        <td style="padding: 12px;">80.0%</td>
+        <td style="padding: 12px; color: #94a3b8;">--</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. Empty cells (--) indicate scores not officially reported for that model.</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 AutoTokenizer, AutoModelForCausalLM, AutoProcessor
+from PIL import Image
+import torch
+
+model_id = "thelamapi/next2.5"
+
+model = AutoModelForCausalLM.from_pretrained(model_id)
+processor = AutoProcessor.from_pretrained(model_id) # For vision.
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+
+# Create a message in chat format
+messages = [
+  {"role": "system","content": [{"type": "text", "text": "You are Next2.5, a smart and concise AI assistant trained by Lamapi. Always respond in the user's language. Proudly made in Turkey."}]},
+
+  {
+      "role": "user","content": [
+      {"type": "text", "text": "Write a highly optimized Rust function to calculate the Fibonacci sequence using memoization"}
+    ]
+  }
+]
+
+# Prepare input with Tokenizer
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=False)
+inputs = processor(text=prompt, return_tensors="pt")
+
+# Remove 'mm_token_type_ids' if it's not needed for text-only generation
+if "mm_token_type_ids" in inputs:
+    del inputs["mm_token_type_ids"]
+
+
+# Output from the model
+output = model.generate(**inputs, do_sample=True, temperature=0.7, max_new_tokens=128)
+print(tokenizer.decode(output[0], skip_special_tokens=True))
+```
+
+---
+
+## 🧩 Model Specifications
+
+| Attribute | Details |
+| :--- | :--- |
+| **Base Architecture** | Qwen 3.5 (Causal Language Model + Vision Encoder) |
+| **Parameters** | 4 Billion |
+| **Context Length** | 262,144 tokens natively (Extensible to 1M+ via YaRN) |
+| **Training Stage** | SFT + RLHF/DPO (Turkish + English focus) |
+| **Hardware** | Runs comfortably on consumer GPUs (e.g., RTX 3060/4060 with 8GB VRAM in FP16, or less via Quantization) |
+| **Capabilities** | Text Generation, Image Understanding, Video Summarization, OCR, Code Generation, Tool Use (Agentic) |
+
+---
+
+## 🎯 Ideal Use Cases
+
+**Next 2.5 (4B)** strikes the perfect balance between high-end reasoning and hardware efficiency. It is perfectly suited for:
+* 🕵️ **Complex Document Analysis:** Upload massive PDFs or images of documents and extract structured, reasoned JSON outputs.
+* 🎓 **Educational Tutoring:** Its native `<think>` capabilities make it an excellent tutor that explains its mathematical steps to students.
+* 🤖 **Autonomous Agents:** Strong `Tool Calling` capabilities let you build desktop agents or web-browsing bots locally.
+* 🇹🇷 **Advanced Turkish NLP:** Finally, a mid-size multimodal model that understands Turkish idioms, grammar, and context as well as it does English.
+
+---
+
+## 📄 License & Open Source
+
+Next 2.5 is released under the **Apache 2.0 License**. We support the open-source community and encourage developers to build commercial applications, conduct research, and innovate freely using this model.
+
+---
+
+## 📞 Contact & Community
+
+* 📧 **Email:**[lamapicontact@gmail.com](mailto:lamapicontact@gmail.com)
+* 🤗 **HuggingFace:** [Lamapi](https://huggingface.co/Lamapi)
+* 💬 **Discord:** [Join the Lamapi Community](https://discord.gg/XgH4EpyPD2)
+
+---
+
+<div align="center" style="margin-top: 40px; padding: 25px; border-top: 1px solid #e2e8f0; background: #f8fafc; border-radius: 8px;">
+  <p style="color: #475569; font-size: 15px; margin: 0;">
+    <strong>Next 2.5</strong> — Sınırları aşan görsel algı ve derin düşünme yeteneği. Türkiye'nin küresel yapay zeka vizyonu. 🌍
+  </p>
+</div>