Pinned Loading

1. Chinese-MedQA-Qwen2 Chinese-MedQA-Qwen2 Public

   基于Qwen2+SFT+DPO的医疗问答系统，项目中使用了LLaMA-Factory用于训练，fastllm和vllm用于推理，

   Python 31 5

2. Travel-Agent-based-on-Qwen2-RLHF Travel-Agent-based-on-Qwen2-RLHF Public

   A travel agent based on Qwen2.5, fine-tuned by SFT + DPO/PPO/GRPO using traveling question-answer dataset, a mindmap can be output using the response. A RAG system is build upon the tuned qwen2, us…

   Python 34 2

3. A-star-search-based-neural-network-performance-comparison A-star-search-based-neural-network-performance-comparison Public

   A comparison of neural networks in limb movement classification tasks based on the A* hyperparameter search algorithm. Our goal is to design an A* algorithm capable of finding the optimal combinat…

   Python 2

4. bert-based-autoregressive-model bert-based-autoregressive-model Public

   Change the Bert model to a GPT-style autoregressive decoder.

   Python 1

5. llm-hub llm-hub Public

   Popular Large Language Model's modeling file and finetune+pretrain scripts, including: llama, grok, chatglm2+3, glm, qwen, qwen2, gpt2, mistral, ...

   Python 1 1