Instructions to use ihoflaz/turkish_llm_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ihoflaz/turkish_llm_lora with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="ihoflaz/turkish_llm_lora")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("ihoflaz/turkish_llm_lora", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use ihoflaz/turkish_llm_lora with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "ihoflaz/turkish_llm_lora" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "ihoflaz/turkish_llm_lora", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/ihoflaz/turkish_llm_lora
- SGLang
How to use ihoflaz/turkish_llm_lora 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 "ihoflaz/turkish_llm_lora" \ --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": "ihoflaz/turkish_llm_lora", "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 "ihoflaz/turkish_llm_lora" \ --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": "ihoflaz/turkish_llm_lora", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use ihoflaz/turkish_llm_lora with Docker Model Runner:
docker model run hf.co/ihoflaz/turkish_llm_lora
🇹🇷 Turkish LLM LoRA - Mistral 7B Fine-tuned Model
Bu model, Mistral-7B üzerine Türkçe metinler ile eğitilmiş bir LoRA (Low-Rank Adaptation) versiyonudur.
Model Bilgileri
- Temel Model: mistralai/Mistral-7B
- Tür: Causal Language Model (CLM)
- Kuantizasyon: 4-bit LoRA
- Eğitim Verisi: Türkçe metinlerden oluşan özel bir veri kümesi
Eğitim Bilgileri
- Donanım: i7 14700KF işlemci, RTX 4070 Super ekran kartı
- Eğitim Süresi: 6 saat
- Ayarlar: 4 epoch, batch size 1, gradient accumulation 16
Veri Seti
- "oscar/unshuffled_deduplicated_tr" veri setinden ilk 10,000 örnek
- Her veri 512 kelimeye kesildi
Değerlendirme
Türkçe cümle tamamlama yaptı, sonuçlar fena değildi.
CO2 Emisyonları
Hesaplanmadı
Model tree for ihoflaz/turkish_llm_lora
Base model
mistralai/Mistral-7B-v0.1