Instructions to use ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M

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 ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M

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 ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M

Use Docker

docker model run hf.co/ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M

Ollama
How to use ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF with Ollama:
```
ollama run hf.co/ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M
```
Unsloth Desktop
Docker Model Runner
How to use ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF with Docker Model Runner:
```
docker model run hf.co/ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M
```

Lemonade

How to use ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Kumru-2B-EPDK-Instruct-GGUF-Q4_K_M

List all available models

lemonade list

Atomic Chat

ogulcanakca commited on Nov 17, 2025

Commit

2076fc6

verified ·

1 Parent(s): ae5b159

Create README.md

Browse files

Files changed (1) hide show

README.md +35 -0

README.md ADDED Viewed

	@@ -0,0 +1,35 @@

+---
+license: apache-2.0
+tags:
+- gguf
+- kumru
+- epdk
+- instruct
+- dpo
+- dapt
+- qlora
+- unsloth
+- mistral
+language:
+- tr
+pipeline_tag: text-generation
+---
+# Model Card
+`ogulcanakca/Kumru-2B-EPDK-Instruct` modelinin (iki aşamalı DAPT + DPO ile eğitilmiş) **GGUF formatına** dönüştürülmüş versiyonlarını içerir.
+Bu dosyalar, `llama.cpp`, `Ollama`, `LM Studio` ve diğer GGUF uyumlu platformlarda **GPU olmadan CPU üzerinde** verimli bir şekilde çalışmak üzere optimize edilmiştir.
+**Ana Model:** 👉 [**ogulcanakca/Kumru-2B-EPDK-Instruct**](https://huggingface.co/ogulcanakca/Kumru-2B-EPDK-Instruct)
+## Eğitim Detayları
+Bu GGUF dosyaları, iki aşamalı bir süreçle eğitilmiş bir modelden dönüştürülmüştür:
+1.  **DAPT:** [`vngrs-ai/Kumru-2B-Base`](https://huggingface.co/vngrs-ai/Kumru-2B-Base) modeli, [`ogulcanakca/epdk_corpus`](https://huggingface.co/datasets/ogulcanakca/epdk_corpus) (domain terminolojisi) üzerinde eğitildi ve [ogulcanakca/Kumru-2B-EPDK-dapt](https://huggingface.co/ogulcanakca/Kumru-2B-EPDK-dapt) oluşturuldu.
+2.  **DPO:** Model, [`ogulcanakca/epdk_dpo`](https://huggingface.co/datasets/ogulcanakca/epdk_dpo) (24.5k+ sentetik `prompt`/`chosen`/`rejected` üçlüsü) veri setiyle DPO yöntemi kullanılarak "sohbet" ve "tercih" için eğitildi ve [ogulcanakca/Kumru-2B-EPDK-DPO](https://huggingface.co/ogulcanakca/Kumru-2B-EPDK-DPO) oluşturuldu..
+3.  **Merge:** [DAPT](https://huggingface.co/ogulcanakca/Kumru-2B-EPDK-dapt) ve [DPO](https://huggingface.co/ogulcanakca/Kumru-2B-EPDK-DPO) adaptörleri, `unsloth` kütüphanesi kullanılarak `Kumru-2B-Base` modeline birleştirildi ve [ogulcanakca/Kumru-2B-EPDK-Instruct](https://huggingface.co/ogulcanakca/Kumru-2B-EPDK-Instruct) oluşturuldu.
+4.  **Convert:** Nihai birleştirilmiş model ([`ogulcanakca/Kumru-2B-EPDK-Instruct`](https://huggingface.co/ogulcanakca/Kumru-2B-EPDK-Instruct)), `unsloth.save_pretrained_gguf` (arkada `llama.cpp` kullanarak) bu GGUF dosyalarına dönüştürüldü.
+**WandB Eğitim Raporu:** 👉 [WandB Raporu (DPO Aşaması)](https://api.wandb.ai/links/ogulcanakca-none/z06caml6)