Instructions to use drkkahraman/cokertme3_0.2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drkkahraman/cokertme3_0.2b with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="drkkahraman/cokertme3_0.2b")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("drkkahraman/cokertme3_0.2b", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use drkkahraman/cokertme3_0.2b 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 drkkahraman/cokertme3_0.2b
# Run inference directly in the terminal:
llama cli -hf drkkahraman/cokertme3_0.2b

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf drkkahraman/cokertme3_0.2b
# Run inference directly in the terminal:
llama cli -hf drkkahraman/cokertme3_0.2b

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 drkkahraman/cokertme3_0.2b
# Run inference directly in the terminal:
./llama-cli -hf drkkahraman/cokertme3_0.2b

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 drkkahraman/cokertme3_0.2b
# Run inference directly in the terminal:
./build/bin/llama-cli -hf drkkahraman/cokertme3_0.2b

Use Docker

docker model run hf.co/drkkahraman/cokertme3_0.2b

LM Studio
Jan

vLLM

How to use drkkahraman/cokertme3_0.2b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drkkahraman/cokertme3_0.2b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drkkahraman/cokertme3_0.2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/drkkahraman/cokertme3_0.2b

SGLang

How to use drkkahraman/cokertme3_0.2b with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "drkkahraman/cokertme3_0.2b" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drkkahraman/cokertme3_0.2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "drkkahraman/cokertme3_0.2b" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drkkahraman/cokertme3_0.2b",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Ollama
How to use drkkahraman/cokertme3_0.2b with Ollama:
```
ollama run hf.co/drkkahraman/cokertme3_0.2b
```

Unsloth Studio

How to use drkkahraman/cokertme3_0.2b 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 drkkahraman/cokertme3_0.2b 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 drkkahraman/cokertme3_0.2b to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for drkkahraman/cokertme3_0.2b to start chatting

Docker Model Runner
How to use drkkahraman/cokertme3_0.2b with Docker Model Runner:
```
docker model run hf.co/drkkahraman/cokertme3_0.2b
```

Lemonade

How to use drkkahraman/cokertme3_0.2b with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull drkkahraman/cokertme3_0.2b

Run and chat with the model

lemonade run user.cokertme3_0.2b-{{QUANT_TAG}}

List all available models

lemonade list

Atomic Chat

TCYZ Cokertme-3 (0.2B)

TCYZ (Türkiye Cumhuriyeti Yapay Zeka) projesinin bir parçası olan Cokertme-3, 208 milyon parametrelik, hafif ama yetenekli bir Türkçe dil modelidir. Doruk Kahraman tarafından geliştirilen bu model, özellikle düşük donanımlı cihazlarda ve yerel sistemlerde yüksek performans göstermesi için optimize edilmiştir.

🚀 Model Detayları

Geliştiren: Doruk Kahraman (TED Bodrum Koleji)
Model Tipi: Llama tabanlı Causal Language Model
Parametre Sayısı: 208.66M
Eğitim Verisi: Özel olarak temizlenmiş ve zenginleştirilmiş Türkçe veri seti
Hassasiyet (Precision): FP16 (Eğitim sırasında Mixed Precision kullanılmıştır)
Kontekst Uzunluğu: 2048 Token

🛠️ Teknik Mimari

Model, aşağıdaki hiper-parametreler ile sıfırdan inşa edilmiştir:

Layers: 8
Attention Heads: 8
Hidden Size: 2048
Intermediate Size: 1376
Vocabulary Size: 5000 (ByteLevelBPE)

💻 Kullanım (Inference)

Bu modeli Hugging Face transformers kütüphanesi ile şu şekilde kullanabilirsiniz:

from transformers import LlamaForCausalLM, GPT2TokenizerFast

model_id = "TCYZ/cokertme3" # Kendi kullanıcı adınla değiştir
tokenizer = GPT2TokenizerFast.from_pretrained(model_id)
model = LlamaForCausalLM.from_pretrained(model_id)

prompt = "Merhaba, nasılsın?"
inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=50)

print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: 16

GGUF

Model size

0.2B params

Architecture

llama

Hardware compatibility

We're not able to determine the quantization variants.

View all variants