sserdoubleh / Research
novel deep learning research works with PaddlePaddle
☆10Updated 2 years ago
Related projects: ⓘ
- chatglm_rlhf_finetuning☆27Updated 11 months ago
- ☆100Updated 3 years ago
- llama inference for tencentpretrain☆95Updated last year
- EVA: Large-scale Pre-trained Chit-Chat Models☆304Updated last year
- Trying to predict a movie's success based on the script (before filming)☆32Updated 4 years ago
- clue chatyuan finetuning☆16Updated 4 months ago
- A framework for cleaning Chinese dialog data☆259Updated 3 years ago
- ☆34Updated 3 years ago
- Unilm for Chinese Chitchat Robot.基于Unilm模型的夸夸式闲聊机器人项目。☆157Updated 3 years ago
- 一个基于预训练的句向量生成工具☆131Updated last year
- Code for CPM-2 Pre-Train☆159Updated last year
- Pytorch model for https://github.com/imcaspar/gpt2-ml☆79Updated 2 years ago
- [LREC] MMChat: Multi-Modal Chat Dataset on Social Media☆96Updated last year
- A official implementation of SARG: A Novel Semi Autoregressive Generator for Multi-turn Incomplete Utterance Restoration☆49Updated 3 years ago
- 中文 Instruction tuning datasets☆112Updated 5 months ago
- moss chat finetuning☆50Updated 4 months ago
- ChatGLM-6B fine-tuning.☆135Updated last year
- GTS Engine: A powerful NLU Training System。GTS引擎(GTS-Engine)是一款开箱即用且性能强大的自然语言理解引擎,聚焦于小样本任务,能够仅用小样本就能自动化生产NLP模型。☆87Updated last year
- Chinese GPT2: pre-training and fine-tuning framework for text generation☆186Updated 3 years ago
- Finetune CPM-1☆75Updated last year
- bge推理优化相关脚本☆18Updated 7 months ago
- LLM with LuXun (鲁迅) style☆75Updated last year
- Kanchil(鼷鹿)是世界上最小的偶蹄目动物,这个开源项目意在探索小模型(6B以下)是否也能具备和人类偏好对齐的能力。☆113Updated last year
- share data, prompt data , pretraining data☆35Updated 9 months ago
- Code and data repo for "DiagGPT"☆37Updated 5 months ago
- 🎵Using GPT2-Chinese to generate rap lyrics🎵☆29Updated last year
- KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation☆463Updated last year
- Chinese Transformer Generative Pre-Training Model☆56Updated 4 years ago
- A Chinese Open-Domain Dialogue System☆310Updated last year
- chatglm-6b微调/LORA/PPO/推理, 样本为自动生成的整数/小数加减乘除运算, 可gpu/cpu☆164Updated last year