SykoSLM
/

SykoLLM-V3.2-Thinking-Beta-Instruct

@@ -1,203 +1,86 @@
 ---
-library_name: transformers
 license: apache-2.0
 datasets:
 - turkish-nlp-suite/InstrucTurca
-language:
-- tr
 ---
-# Model Card for Model ID
-<!-- Provide a quick summary of what the model is/does. -->
-## Model Details
-### Model Description
-<!-- Provide a longer summary of what this model is. -->
-This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
-### Model Sources [optional]
-<!-- Provide the basic links for the model. -->
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-## Uses
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-### Direct Use
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-[More Information Needed]
-### Downstream Use [optional]
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-[More Information Needed]
-### Out-of-Scope Use
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-[More Information Needed]
-## Bias, Risks, and Limitations
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-[More Information Needed]
-### Recommendations
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
-## How to Get Started with the Model
-Use the code below to get started with the model.
-[More Information Needed]
-## Training Details
-### Training Data
-<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
-[More Information Needed]
-### Training Procedure
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-#### Preprocessing [optional]
-[More Information Needed]
-#### Training Hyperparameters
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-#### Speeds, Sizes, Times [optional]
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-[More Information Needed]
-## Evaluation
-<!-- This section describes the evaluation protocols and provides the results. -->
-### Testing Data, Factors & Metrics
-#### Testing Data
-<!-- This should link to a Dataset Card if possible. -->
-[More Information Needed]
-#### Factors
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-[More Information Needed]
-#### Metrics
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-[More Information Needed]
-### Results
-[More Information Needed]
-#### Summary
-## Model Examination [optional]
-<!-- Relevant interpretability work for the model goes here -->
-[More Information Needed]
-## Environmental Impact
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-## Technical Specifications [optional]
-### Model Architecture and Objective
-[More Information Needed]
-### Compute Infrastructure
-[More Information Needed]
-#### Hardware
-[More Information Needed]
-#### Software
-[More Information Needed]
-## Citation [optional]
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-**BibTeX:**
-[More Information Needed]
-**APA:**
-[More Information Needed]
-## Glossary [optional]
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-[More Information Needed]
-## More Information [optional]
-[More Information Needed]
-## Model Card Authors [optional]
-[More Information Needed]
-## Model Card Contact
-[More Information Needed]

 ---
+language:
+- tr
 license: apache-2.0
+tags:
+- turkish
+- llm
+- instruct
+- text-generation
+- custom-model
+- syko
 datasets:
 - turkish-nlp-suite/InstrucTurca
+- wikipedia
+pipeline_tag: text-generation
+inference: false
 ---
+# SykoLLM-V3.2-Thinking-Beta-Instruct (300M) 🇹🇷
+![Status](https://img.shields.io/badge/Status-Beta-yellow) ![Language](https://img.shields.io/badge/Language-Turkish-red) ![Parameter](https://img.shields.io/badge/Parameters-300M-blue)
+**SykoLLM-V3.2**, tamamen sıfırdan eğitilmiş (built from scratch), Türkçe dil yapısına özel olarak optimize edilmiş **300 Milyon parametreli** deneysel bir Büyük Dil Modelidir (LLM).
+Bu model, mevcut popüler modellerin (Llama, Qwen vb.) üzerine fine-tune **DEĞİLDİR**. Mimarisi, tokenizer'ı ve ağırlıkları tamamen özgün bir şekilde geliştirilmiştir.
+## 🌟 Modelin Hikayesi ve Özellikleri
+Bu proje, "Büyük modeller her zaman daha iyidir" algısına karşı, verimli ve optimize edilmiş küçük modellerin neler yapabileceğini test etmek amacıyla geliştirilmiştir.
+- **Tamamen Yerli Tokenizer:** 50.000 kelimelik (vocab size) özel tokenizer eğitildi. Türkçe'nin eklemeli yapısına (agglutinative) tam uyumlu olması için tasarlandı. Bu sayede model, diğer çok dilli modellere göre daha az token ile daha fazla Türkçe içerik ifade edebilir.
+- **Sıfırdan Eğitim (Pre-training):** Model, T4 GPU'lar üzerinde Wikipedia verileri ile dilin temel yapısını (morfoloji ve sentaks) öğrenmek için yüksek öğrenme oranı (High Learning Rate) ile "agresif" bir başlangıç eğitimi aldı.
+- **Instruct Tuning:** Temel eğitimin ardından, A100 GPU üzerinde 700.000+ satırlık Instruct (Talimat) verisi ile sohbet yeteneği kazandırıldı.
+- **Donanım & Optimizasyon:** Eğitim sürecinde `Flash Attention 2`, `bfloat16` ve `torch.compile` teknolojileri kullanılarak A100 GPU'nun sınırları zorlandı.
+## ⚙️ Teknik Detaylar
+| Özellik | Değer |
+| :--- | :--- |
+| **Model Tipi** | Causal Decoder-Only Transformer |
+| **Parametre Sayısı** | ~300 Milyon |
+| **Context Window** | 1024 Token |
+| **Vocab Size** | 50.257 (Özel Türkçe Tokenizer) |
+| **Eğitim Donanımı** | NVIDIA T4 (Pre-train) -> NVIDIA A100 (SFT) |
+| **Eğitim Formatı** | Instruct (User/Assistant) |
+## 🚀 Nasıl Kullanılır?
+Model özel mimari ve tokenizer içerdiği için `trust_remote_code=True` parametresi önemlidir.
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+model_name = "syko818121/SykoLLM-V3.2-Thinking-Beta-Instruct"
+# Model ve Tokenizer Yükleme
+tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(
+    model_name,
+    torch_dtype=torch.bfloat16,
+    device_map="auto",
+    trust_remote_code=True
+)
+# Prompt Formatı
+system_prompt = "Sen yardımsever bir yapay zeka asistanısın."
+user_input = "Yapay zeka gelecekte dünyayı nasıl değiştirecek?"
+prompt = f"### user: {user_input}\n### assistant:"
+# Inference
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+with torch.no_grad():
+    outputs = model.generate(
+        **inputs,
+        max_new_tokens=256,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9,
+        repetition_penalty=1.2,
+        pad_token_id=tokenizer.eos_token_id
+    )
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))