Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+Gemma_E4B_Kizagan_Abliterated-F16.gguf filter=lfs diff=lfs merge=lfs -text
+Gemma_E4B_Kizagan_Abliterated-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text

Gemma_E4B_Kizagan_Abliterated-F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:396f8a32d78659f16c53906d339cf71e0d792bc9852ef3abc69261f761460e20
+size 15053095744

Gemma_E4B_Kizagan_Abliterated-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d52e2429067e4271dd9d961fdc72adf637fd49c5b781e70be0c0634033053645
+size 5335290688

README.md

@@ -0,0 +1,110 @@
+---
+language:
+  - tr
+  - en
+license: apache-2.0
+tags:
+  - gguf
+  - turkish
+  - uncensored
+  - abliterated
+  - gemma
+  - gemma-4
+  - kizagan
+  - llama.cpp
+  - lm-studio
+  - ollama
+pipeline_tag: text-generation
+base_model: canyrtcn/Gemma_E4B_Kizagan_Abliterated
+library_name: llama.cpp
+---
+
+# 🔓 Gemma E4B Kızagan Abliterated — GGUF
+
+[**canyrtcn/Gemma_E4B_Kizagan_Abliterated**](https://huggingface.co/canyrtcn/Gemma_E4B_Kizagan_Abliterated) modelinin **GGUF quantize edilmiş** versiyonları.
+
+---
+
+## 📦 Bu repoda bulunan quant'lar
+
+| Dosya | Quant | Boyut | Kalite | Önerilen |
+|---|---|---|---|---|
+| `Gemma_E4B_Kizagan_Abliterated-Q4_K_M.gguf` | Q4_K_M | ~5 GB | ⭐⭐⭐⭐ | 8GB VRAM, dengeli kullanım |
+| `Gemma_E4B_Kizagan_Abliterated-F16.gguf` | F16 | ~15 GB | ⭐⭐⭐⭐⭐ | 16GB+ VRAM, maksimum kalite |
+
+---
+
+## 🚀 Kullanım
+
+### 🦙 llama.cpp
+
+```bash
+# Q4_K_M ile hızlı kullanım
+llama-cli -hf canyrtcn/Gemma_E4B_Kizagan_Abliterated-GGUF:Q4_K_M \
+  --chat-template gemma \
+  -p "Merhaba, kendini tanıtır mısın?"
+
+# F16 ile maksimum kalite
+llama-cli -hf canyrtcn/Gemma_E4B_Kizagan_Abliterated-GGUF:F16 \
+  --chat-template gemma \
+  -p "Bana İstanbul'un fethini hikaye şeklinde anlat."
+```
+
+### 🖥️ LM Studio
+
+1. LM Studio'da arama çubuğuna `canyrtcn/Gemma_E4B_Kizagan_Abliterated-GGUF` yazın
+2. İstediğiniz quant'ı seçip indirin
+3. Chat template olarak **Gemma** seçili olduğundan emin olun
+
+### 🐳 Ollama
+
+```bash
+# Manuel GGUF ile
+ollama create kizagan-uncensored -f Modelfile
+```
+
+`Modelfile`:
+```
+FROM ./Gemma_E4B_Kizagan_Abliterated-Q4_K_M.gguf
+PARAMETER temperature 0.7
+PARAMETER top_p 0.95
+PARAMETER top_k 64
+TEMPLATE """{{ if .System }}<|turn>system
+{{ .System }}<turn|>
+{{ end }}<|turn>user
+{{ .Prompt }}<turn|>
+<|turn>model
+"""
+```
+
+---
+
+## 📐 Model Hakkında
+
+Bu GGUF'lar, **canyrtcn/Gemma_E4B_Kizagan_Abliterated** modelinden dönüştürülmüştür:
+
+- **Temel model:** Gemma 4 E4B-it (Google DeepMind)
+- **Türkçe SFT:** AlicanKiraz0/Kizagan-E4B-Turkish-Reasoning-Model (540K satır)
+- **Abliteration:** Reddetme davranışı kaldırıldı (uncensored)
+- **Mimari:** Gemma 4 (MoE-style PLE, 7.5B toplam / 4B efektif)
+- **Context:** 131K token
+
+---
+
+## ⚠️ Uyarı
+
+Bu model **sansürsüzdür (uncensored)**. Hassas veya filtrelenmemiş içerik üretebilir. Kullanım sorumluluğu size aittir.
+
+---
+
+## 📜 Lisans
+
+Apache 2.0. Google Gemma [Terms of Use](https://ai.google.dev/gemma/terms) koşullarına tabidir.
+
+---
+
+## 🔗 Bağlantılar
+
+- Ana model (safetensors): [canyrtcn/Gemma_E4B_Kizagan_Abliterated](https://huggingface.co/canyrtcn/Gemma_E4B_Kizagan_Abliterated)
+- Orijinal Kızagan: [AlicanKiraz0/Kizagan-E4B](https://huggingface.co/AlicanKiraz0/Kizagan-E4B-Turkish-Reasoning-Model)
+- Temel model: [google/gemma-4-E4B-it](https://huggingface.co/google/gemma-4-E4B-it)