Türkçe
Collection
Türkçe dilinde de eğitilmiş, anlamlı ve faydalı Türkçe yanıt verebilen modeller. Llama modelleri Türkçe konusunda pek yeterli değil maalesef. • 38 items • Updated • 2
How to use matrixportalx/Turkce-LLM-GGUF with Transformers:
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("matrixportalx/Turkce-LLM-GGUF", device_map="auto")How to use matrixportalx/Turkce-LLM-GGUF with llama.cpp:
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf matrixportalx/Turkce-LLM-GGUF:Q4_0 # Run inference directly in the terminal: llama cli -hf matrixportalx/Turkce-LLM-GGUF:Q4_0
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf matrixportalx/Turkce-LLM-GGUF:Q4_0 # Run inference directly in the terminal: llama cli -hf matrixportalx/Turkce-LLM-GGUF:Q4_0
# 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 matrixportalx/Turkce-LLM-GGUF:Q4_0 # Run inference directly in the terminal: ./llama-cli -hf matrixportalx/Turkce-LLM-GGUF:Q4_0
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 matrixportalx/Turkce-LLM-GGUF:Q4_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf matrixportalx/Turkce-LLM-GGUF:Q4_0
docker model run hf.co/matrixportalx/Turkce-LLM-GGUF:Q4_0
How to use matrixportalx/Turkce-LLM-GGUF with Ollama:
ollama run hf.co/matrixportalx/Turkce-LLM-GGUF:Q4_0
How to use matrixportalx/Turkce-LLM-GGUF with Docker Model Runner:
docker model run hf.co/matrixportalx/Turkce-LLM-GGUF:Q4_0
How to use matrixportalx/Turkce-LLM-GGUF with Lemonade:
# Download Lemonade from https://lemonade-server.ai/ lemonade pull matrixportalx/Turkce-LLM-GGUF:Q4_0
lemonade run user.Turkce-LLM-GGUF-Q4_0
lemonade list
| 🚀 Download | 🔢 Type | 📝 Description |
|---|---|---|
| Download | Q4 0 | Standard 4-bit (fast on ARM) |
💡 Q4 K M provides the best balance for most use cases
4-bit
Base model
meta-llama/Meta-Llama-3-8B-Instruct