Instructions to use emirkaanozdemr/fok-2b-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use emirkaanozdemr/fok-2b-instruct with Transformers:

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

pipe = pipeline("text-generation", model="emirkaanozdemr/fok-2b-instruct")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("emirkaanozdemr/fok-2b-instruct", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use emirkaanozdemr/fok-2b-instruct with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/emirkaanozdemr/fok-2b-instruct

SGLang

How to use emirkaanozdemr/fok-2b-instruct 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 "emirkaanozdemr/fok-2b-instruct" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emirkaanozdemr/fok-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "emirkaanozdemr/fok-2b-instruct" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "emirkaanozdemr/fok-2b-instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Studio new

How to use emirkaanozdemr/fok-2b-instruct 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 emirkaanozdemr/fok-2b-instruct 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 emirkaanozdemr/fok-2b-instruct to start chatting

Using HuggingFace Spaces for Unsloth

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

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="emirkaanozdemr/fok-2b-instruct",
    max_seq_length=2048,
)

Docker Model Runner
How to use emirkaanozdemr/fok-2b-instruct with Docker Model Runner:
```
docker model run hf.co/emirkaanozdemr/fok-2b-instruct
```

Fok-2B Instruct

Overview / Genel Bakış

Fok-2B Instruct, VNGRS AI Kumru-2B modeli üzerine LoRA ile fine-tune edilmiş bir AI asistan modelidir.
Bu model, özellikle Kutup Araştırma İstasyonları senaryolarında sensör verilerini analiz ederek olası riskleri belirlemek ve detaylı öneriler üretmek için eğitilmiştir.

Kullanılan veri seti: emirkaanozdemr/fok-2b-dataset

Fok-2B Instruct is a LoRA fine-tuned AI assistant model built on VNGRS AI Kumru-2B.
It is designed to analyze sensor data from Polar Research Stations, detect potential risks, and generate detailed recommendations.

Dataset used: emirkaanozdemr/fok-2b-dataset

Features / Özellikler

Input: Sensör verileri ve senaryo açıklaması
Output: Türkçe olası risk analizi ve öneriler
LoRA fine-tune ile optimize edilmiş hafif model
4-bit precision ile düşük VRAM kullanımı
Input: Sensor data and scenario description
Output: Risk analysis and detailed recommendations in Turkish
Lightweight model optimized with LoRA fine-tuning
4-bit precision for low VRAM usage

Usage / Kullanım

from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("emirkaanozdemr/kumru-2b")
model = AutoModelForCausalLM.from_pretrained("emirkaanozdemr/kumru-2b")

instruction = "Sen bir kutup araştırma istasyonunda çalışan AI asistansın. Olası riskleri değerlendir."
input_data = {
    "temperature": -15.0,
    "co2": 600,
    "energy": 0.8,
    "anomaly_score": 0.75,
    "scenario": "Emergency stop activated"
}

prompt = f"""<|user|>
{instruction}

Verilen sensör verilerini kullan:
Temperature: {input_data['temperature']}°C
CO2: {input_data['co2']} ppm
Energy: {input_data['energy']}
Anomaly score: {input_data['anomaly_score']}
Scenario: {input_data['scenario']}

Türkçe olarak olası riskleri açıkla ve detaylı öneriler üret.

<|assistant|>
"""

inputs = tokenizer(prompt, return_tensors="pt")
outputs = model.generate(**inputs, max_length=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Downloads last month: -; Downloads are not tracked for this model. How to track

Model tree for emirkaanozdemr/fok-2b-instruct

Base model

vngrs-ai/Kumru-2B

Finetuned

(9)

this model

Dataset used to train emirkaanozdemr/fok-2b-instruct

Collection including emirkaanozdemr/fok-2b-instruct

Fok LLM Family

Collection

Fok LLM family for TEKNOFEST Lise Öğrencileri Kutup Araştırma Projeleri Yarışması by Emir Kaan Özdemir • 2 items • Updated Mar 15 • 1