Instructions to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SarpBnlcn/BIST-LLM-8B-Turkish-Finance",
	filename="BIST-Expert-Q4_K_M.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance: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 SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance: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 SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

Use Docker

docker model run hf.co/SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

LM Studio
Jan

vLLM

How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SarpBnlcn/BIST-LLM-8B-Turkish-Finance"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SarpBnlcn/BIST-LLM-8B-Turkish-Finance",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

Ollama
How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with Ollama:
```
ollama run hf.co/SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M
```

Unsloth Studio

How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance 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 SarpBnlcn/BIST-LLM-8B-Turkish-Finance 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 SarpBnlcn/BIST-LLM-8B-Turkish-Finance to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SarpBnlcn/BIST-LLM-8B-Turkish-Finance to start chatting

How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with Docker Model Runner:
```
docker model run hf.co/SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M
```

Lemonade

How to use SarpBnlcn/BIST-LLM-8B-Turkish-Finance with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SarpBnlcn/BIST-LLM-8B-Turkish-Finance:Q4_K_M

Run and chat with the model

lemonade run user.BIST-LLM-8B-Turkish-Finance-Q4_K_M

List all available models

lemonade list

🏦 BIST-LLM-8B-Turkish-Finance

BIST-LLM-8B-Turkish-Finance, Borsa İstanbul (BIST) şirketlerinin finansal sağlığını analiz etmek için özelleştirilmiş bir büyük dil modelidir. Model, finansal oran (ratio) analizi ve Z-Score metodolojisi kullanarak şirketlerin sektörel performansını değerlendirmeye odaklanır.

Model, Meta Llama 3.1 8B Instruct mimarisi üzerine kurulmuş olup Türkçe finansal analiz görevleri için ince ayar (fine-tuning) yapılmıştır.

🎯 Temel Özellikler

📊 BIST Ekosistemi Odaklı Analiz

BIST şirketlerinin finansal rasyolarını sektörel ortalamalarla karşılaştırarak analiz yapabilir.

📈 Z-Score Metodolojisi

Finansal rasyoların sektör ortalamasından sapmasını hesaplayarak olası finansal riskleri ve anomalileri tespit edebilir.

🔍 Temel Analiz Yetkinliği

Model aşağıdaki finansal metrikleri yorumlayabilir:

F/K (P/E)
PD/DD (P/B)
FD/FAVÖK (EV/EBITDA)
ROE
Borçluluk oranları
Karlılık göstergeleri

⚖️ Regülasyon Bilgisi

Model, Türkiye finansal raporlama standartları (TFRS) ve SPK düzenlemeleri hakkında temel teknik bilgi sunabilir.

📊 Model Teknik Detayları

Özellik	Değer
Base Model	meta-llama/Meta-Llama-3.1-8B-Instruct
Quantization	GGUF (Q4_K_M)
Fine-Tuning	QLoRA (4-bit)
Domain	Turkish Financial Analysis
Focus	BIST Ratio Analysis

🤝 Veri Seti ve Atıf

Modelin finansal analiz yetkinliği, Alican Kiraz (@AlicanKiraz0) tarafından hazırlanan Turkish Finance SFT Dataset kullanılarak geliştirilmiştir.

Bu veri seti yaklaşık 10 milyon token içeren Türkçe finansal içerikten oluşmaktadır ve modelin aşağıdaki alanlarda uzmanlaşmasına yardımcı olmuştur:

finansal analiz
teknik kavramlar
finansal oran yorumlama
regülasyon bilgisi

🚀 Kullanım (Önerilen System Prompt)

Modeli finansal analiz görevlerinde daha tutarlı çalıştırmak için aşağıdaki sistem talimatı önerilir:

Sen Türkiye finansal piyasaları konusunda uzmanlaşmış bir finansal analiz asistanısın.

Görevin:

finansal rasyoları analiz etmek

Z-Score metodolojisini kullanarak yorum yapmak

bilanço kalemlerini açıklamak

SPK ve TFRS çerçevesinde teknik bilgi sunmak

Yanıtlarında objektif, teknik ve veri odaklı bir dil kullan.

⚠️ Sorumluluk Reddi

Bu model tarafından üretilen bilgiler yalnızca bilgilendirme amaçlıdır ve yatırım tavsiyesi değildir.

Finansal kararlar almadan önce lisanslı bir yatırım danışmanına başvurmanız önerilir.

Downloads last month: 18

GGUF

Model size

8B params

Architecture

llama

Hardware compatibility

4-bit

Model tree for SarpBnlcn/BIST-LLM-8B-Turkish-Finance

Base model

meta-llama/Llama-3.1-8B

Finetuned

meta-llama/Llama-3.1-8B-Instruct

Quantized

(644)

this model

SarpBnlcn
/

BIST-LLM-8B-Turkish-Finance