Ali-Yaser

This model was finetuned and converted to GGUF format using Unsloth. Example usage: - For text only LLMs: llama-cli --hf repoid/modelname -p "why is the sky blue?" - For multimodal models: llama-mtmd-cli -m modelname.gguf --mmproj mmprojfile.gguf Available Model files: - `qwen3-4b-instruct-2507.F16.gguf` Ollama An Ollama Modelfile is included for easy deployment. This model is a fine-tuned version for Turkish and is currently at version v0.1. The datasets used are publicly available.

(important warning) If you are using the model in GGUF mode, you need to configure the prompt template. Here is the recommended prompt template: PARAMETER stop "### Instruction:" PARAMETER stop "### Response:" - GGUF MODELS https://huggingface.co/mradermacher/LLaMA-3.1-turkis-8b-GGUF; https://huggingface.co/mradermacher/LLaMA-3.1-turkis-8b-i1-GGUF Thanks for mradermacher for converting the model to GGUF format. - Developed by: Ali-Yaser - License: llama 3.1 - Finetuned from model : unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit This model, Llama 3.1 8b, has been fine-tuned using a 1M token dataset, and the model version is v0.2. The model is newer and MAY PROVIDE INCORRECT RESPONSES.