WiroAI

This LoRA is trained for anyone who like Hyunjin from Stray Kids. - Developed by: [Wiro AI - ML Team] - Shared by: Wiro AI You should use `hyunjinwiro` to trigger the image generation.

🚀 Meet with WiroAI/WiroAI-Finance-Qwen-1.5B! A robust language model with more finance knowledge support! 🚀 - Fine-tuned with 500,000+ high-quality finance instructions. (Josephgflowers/Finance-Instruct-500k) - LoRA method was used for fine-tuning without quantization. - Adapted to finance expertise. - Built on Qwen's architecture 📝 Model Details The model is the finance data fine-tuned version of Qwen model family. This model has been trained using Supervised Fine-Tuning (SFT) on carefully curated high-quality finance instructions. Please note that training data includes English and Chinese instructions, and this model rarely mix the two languages. 🤝 License and Usage This model is provided under apache 2.0 license. Please review the license terms before use. 📫 Contact and Support For questions, suggestions, and feedback, please open an issue on HuggingFace or contact us directly from our website.

This LoRA is trained for anyone who like Momo from Twice. - Developed by: [Wiro AI - ML Team] - Shared by: Wiro AI You should use `mmowiro` to trigger the image generation.

- Developed by: [Wiro AI - ML Team] - Shared by: Wiro AI You should use `lgdsgn` to trigger the image generation.

This is a finetune of Qwen2.5-Instruct on WiroAI/dolphin-r1-turkish. - DeepSeek's distilled models sometimes reason in Chinese or English even though prompted in another language. - Open-Source models still need improvement on relatively low-resource languages. - A motivation to reproduce R1 and contribute to the community. - We train the model on the WiroAI/dolphin-r1-turkish for 2 epochs. We use learning rate of 1e-5 and max seq length 4096. The training follows a cosine learning rate schedule with a 10% warmup phase. - Training took 3 days in 8xA6000 ADA cluster. - Normally, R1 team compares the performance of OpenR1 models to DeepSeek-Distill-Qwen-7B and OpenThinker-7B using lighteval. However, the datasets are only MATH oriented so not to conclude anything we won't disclose the default results. You can find the training and evaluation code at: https://github.com/huggingface/open-r1/ - We observed that reasoning process has slightly improved. Our model thinks more clearly in Turkish compared to the DeepSeek's reasoning model. - This model trained for experimental motives and any benchmark evaluation is appreciated. Please be aware that this model will be producing more tokens compared to normal models and will consume more VRAM during inference. - If you are willing to evaluate this model please make sure that model will be allowed to produce enough tokens. Generate until requests that restrict the model to output less than 4000 tokens will lead to poor results. - We believe democratized and culturally improved open-source models will be through sharing and experiments! 🤗 Community - We would like to thank Huggingface Staff and everyone who contributed to the Open-R1 project!

🚀 Meet with WiroAI/WiroAI-Finance-Gemma-9B! A robust language model with more finance knowledge support! 🚀 - Fine-tuned with 500,000+ high-quality finance instructions. (Josephgflowers/Finance-Instruct-500k) - LoRA method was used for fine-tuning without quantization. - Adapted to finance expertise. - Built on Google's cutting-edge Gemma architecture 📝 Model Details The model is the finance data fine-tuned version of Google's innovative Gemma model family. This model has been trained using Supervised Fine-Tuning (SFT) on carefully curated high-quality finance instructions. 🤝 License and Usage This model is provided under Gemma license. Please review the license terms before use. 📫 Contact and Support For questions, suggestions, and feedback, please open an issue on HuggingFace or contact us directly from our website.

Model Description This LoRA is trained for anyone who likes Pokemon style. You can visit our website to check other models https://wiro.ai/.