# Large Language Model Fine-tuning

A Python programming specialized model fine-tuned based on Qwen/Qwen3-30B-A3B, focusing on code generation tasks

This model is a text generation model fine-tuned based on Qwen2.5-14B-Instruct and trained using the TRL library.

Z1 is a large language model based on Qwen2.5-Coder-7B-Instruct, focusing on efficient reasoning through thought migration.

A citation intent classification model fine-tuned based on Qwen 2.5 14B Instruct, specifically designed for citation intent classification in scientific publications.

LLM2Vec is a simple method to convert decoder-only large language models into text encoders by enabling bidirectional attention, masked next-token prediction, and unsupervised contrastive learning.

MiniCPM-Reranker is a bilingual text reranking model jointly developed by FaceWall Intelligence, Tsinghua University's Natural Language Processing Laboratory, and Northeastern University's Information Retrieval Group, featuring exceptional Chinese-English and cross-language reranking capabilities.

ChemVLM is a multimodal large language model focused on applications in the chemical field, combining text and image processing capabilities.

A text style transfer model fine-tuned based on Yi-6b, capable of rewriting input texts into the literary style of 'Romance of the Three Kingdoms'

A Spanish clickbait news summarization model fine-tuned on the NoticIA dataset, capable of revealing the true content behind sensational headlines

OneKE is a bilingual large language model jointly developed by Ant Group and Zhejiang University, focusing on knowledge extraction tasks and supporting multi-domain information extraction in Chinese and English.

A PET report auto-impression generation model fine-tuned based on the BioBART model, used to generate personalized clinical impressions from PET examination findings.

A chat model trained on multiple Korean instruction datasets based on the EleutherAI/polyglot-ko-5.8b model

A causal language model based on the Pythia-6.9b foundation model, fine-tuned using Anthropic's hh-rlhf dataset for supervised training

CoEdIT-xxl is a large-scale text editing model fine-tuned based on the google/flan-t5-xxl model, specifically designed for text revision tasks following instructions.