Instructions to use fatihburakkaragoz/EksiZeka with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use fatihburakkaragoz/EksiZeka with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="fatihburakkaragoz/EksiZeka",
	filename="eksi-fp16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use fatihburakkaragoz/EksiZeka with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fatihburakkaragoz/EksiZeka:Q4_1
# Run inference directly in the terminal:
llama-cli -hf fatihburakkaragoz/EksiZeka:Q4_1

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf fatihburakkaragoz/EksiZeka:Q4_1
# Run inference directly in the terminal:
llama-cli -hf fatihburakkaragoz/EksiZeka:Q4_1

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf fatihburakkaragoz/EksiZeka:Q4_1
# Run inference directly in the terminal:
./llama-cli -hf fatihburakkaragoz/EksiZeka:Q4_1

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf fatihburakkaragoz/EksiZeka:Q4_1
# Run inference directly in the terminal:
./build/bin/llama-cli -hf fatihburakkaragoz/EksiZeka:Q4_1

Use Docker

docker model run hf.co/fatihburakkaragoz/EksiZeka:Q4_1

LM Studio
Jan
Ollama
How to use fatihburakkaragoz/EksiZeka with Ollama:
```
ollama run hf.co/fatihburakkaragoz/EksiZeka:Q4_1
```

Unsloth Studio

How to use fatihburakkaragoz/EksiZeka with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for fatihburakkaragoz/EksiZeka to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for fatihburakkaragoz/EksiZeka to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for fatihburakkaragoz/EksiZeka to start chatting

Atomic Chat new
Docker Model Runner
How to use fatihburakkaragoz/EksiZeka with Docker Model Runner:
```
docker model run hf.co/fatihburakkaragoz/EksiZeka:Q4_1
```

Lemonade

How to use fatihburakkaragoz/EksiZeka with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull fatihburakkaragoz/EksiZeka:Q4_1

Run and chat with the model

lemonade run user.EksiZeka-Q4_1

List all available models

lemonade list

EkşiZeka-2.0

Ekşi Sözlük'ün tarzını taşıyan Türkçe LLM

EkşiZeka-2.0, Trendyol-LLM-7b-chat-v0.1 taban modeli üzerine LoRA ile eğitilmiş, tamamen Ekşi Sözlük verileriyle optimize edilmiş yaratıcı-yazı odaklı bir dil modelidir.

Model; mizah, ironi, kültür, keskin yorum ve kişisel anlatım dilini yüksek doğrulukla taklit eder.

Hugging Face: https://huggingface.co/0xcdli/EksiZeka-2.0

Web demo (bakımda): https://eksifikir.com

Özellikler

Ekşi Sözlük tarzında kısa ve çarpıcı üretimler
Alan (domain) kontrollü üretim
GGUF quant modeller ile hızlı yerel kullanım
Tamamı Türkçe veriyle eğitilmiş özgün bir stil modeli

Prompt Formatı

<<DOMAIN: mizah>>Başlık: iphone 16 Ekşi Sözlük tarzında kısa, çarpıcı bir entry yaz.

Eğitim Özeti

Parametre	Detay
Taban Model	Trendyol-LLM-7b-chat-v0.1
Yöntem	LoRA (Supervised Fine-Tuning)
Veri	~850k ham entry → ~500k temizlenmiş
Domain'ler	politika, mizah, kişisel, akademik
Max Seq Len	1024 (packing aktif)
Epoch	3
LoRA	r=32, alpha=64, dropout=0.05
Donanım	RTX 4090
Süre	~42 saat

Dosyalar

Dosya	Açıklama
`eksi-q4_1.gguf`	Hafif quant model
`eksi-fp16.gguf`	Tam doğruluk GGUF
`tokenizer.*`	Tokenizer dosyaları
`config.json`	Model ayarları

Lisans

Ticari olmayan kullanım.

Detaylar için LICENSE dosyasına bakınız.

İletişim

Mail: fatihburak@pm.me
X/Twitter: https://x.com/0xcdli

EkşiZeka ile başlık at, entry aksın.

Downloads last month: 11

GGUF

Model size

7B params

Architecture

llama

Hardware compatibility

4-bit

View +1 variant

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for fatihburakkaragoz/EksiZeka

Base model

Trendyol/Trendyol-LLM-7b-chat-v0.1

Quantized

(4)

this model