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

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

Eğitim Detayları

Bu GGUF dosyaları, iki aşamalı bir süreçle eğitilmiş bir modelden dönüştürülmüştür:

DAPT: vngrs-ai/Kumru-2B-Base modeli, ogulcanakca/epdk_corpus (domain terminolojisi) üzerinde eğitildi ve ogulcanakca/Kumru-2B-EPDK-dapt oluşturuldu.
DPO: Model, 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 oluşturuldu..
Merge: DAPT ve DPO adaptörleri, unsloth kütüphanesi kullanılarak Kumru-2B-Base modeline birleştirildi ve ogulcanakca/Kumru-2B-EPDK-Instruct oluşturuldu.
Convert: Nihai birleştirilmiş model (ogulcanakca/Kumru-2B-EPDK-Instruct), llama.cpp kullanarak bu GGUF dosyalarına dönüştürüldü.

WandB Eğitim Raporu: 👉 WandB Raporu (DPO Aşaması)

Downloads last month: 41

GGUF

Model size

2B params

Architecture

llama

Hardware compatibility

4-bit

5-bit

6-bit

8-bit

16-bit

Model tree for ogulcanakca/Kumru-2B-EPDK-Instruct-GGUF

Base model

vngrs/Kumru-2B-Base

Finetuned

ogulcanakca/Kumru-2B-EPDK-Instruct

Quantized

(3)

this model