# LoRA Efficient Training

A pseudo-reasoning expert model fine-tuned from Google Gemma-3-4b-pt, designed for structured reasoning/pseudo-inductive reasoning

A post-trained version based on the Qwen/Qwen2.5-14B-Instruct-1M model, using LoRA-8-4-0.0001-cosine-32-16 configuration, trained on train_data_v1.0.

Financial domain-specific language model based on Qwen architecture, fine-tuned with 500k+ financial instructions

Llama3.1-Neo-1B-100w is an efficient language model pruned to 1.4B parameters from Meta-Llama-3.1-8B-Instruct and fine-tuned using the LLM-Neo method (combining LoRA and knowledge distillation). The training data consists of 1 million samples from BAAI/Infinity-Instruct.

This is a Q&A model fine-tuned on Polish instruction datasets based on the Qra-1b model, primarily used to answer user questions.

ZhiLu is a financial large language model developed based on Chinese Alpaca2-13B, achieving capability leaps through massive incremental pre-training with Chinese and English corpora and high-quality instruction data alignment, with a focus on enhancing performance in the financial domain.