qhduan / CodeGen
CodeGen is an open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
☆12Updated 2 years ago
Alternatives and similar repositories for CodeGen:
Users that are interested in CodeGen are comparing it to the libraries listed below
- 实现Blip2RWKV+QFormer的多模态图文对话大模型,使用Two-Step Cognitive Psychology Prompt方法,仅3B参数的模型便能够出现类人因果 思维链。对标MiniGPT-4,ImageBind等图文对话大语言模型,力求以更小的算力和资源实…☆37Updated last year
- 兼容 GPT2、Bloom 等 Pytorch 框架下的语言模型、人工智能标记语言 (AIML) 和任务型对话系统 (Task) 的深度中文智能对话机器人框架☆26Updated last year
- AGM阿格姆:AI基因图谱模型,从token-weight权重微粒角度,探索AI模型,GPT\LLM大模型的内在运作机制。☆28Updated last year
- 中文文本改写☆19Updated 4 years ago
- 极简爬虫工作流☆41Updated last year
- Large-scale exact string matching tool☆15Updated 2 months ago
- 实现一种多Lora权值集成切换+Zero-Finetune零微调增强的跨模型技术方案,LLM-Base+LLM-X+Alpaca,初期,LLM-Base为Chatglm6B底座模型,LLM-X是LLAMA增强模型。该方案简易高效,目标是使此类语言模型能够低能耗广泛部署,并最…☆117Updated last year
- 词、句拼音转汉字、拼音分割、拼音补全、pygame输入中文☆15Updated 4 years ago
- Silk Road will be the dataset zoo for Luotuo(骆驼). Luotuo is an open sourced Chinese-LLM project founded by 陈启源 @ 华中师范大学 & 李鲁鲁 @ 商汤科技 & 冷子…☆38Updated last year
- Tracking the hot Github repos and update daily 每天自动追踪Github热门项目☆44Updated this week
- GPT+神器,简单实用的一站式AGI架构,内置本地化,LLM模型,agent,矢量数据库,智能链chain☆48Updated last year
- 全球首个StableVicuna中文优化版。☆64Updated last year
- 百度QA100万数据集☆47Updated last year
- 骆驼QA,中文大语 言阅读理解模型。☆74Updated last year
- ✅4g GPU可用 | 简易实现ChatGLM单机调用多个计算设备(GPU、CPU)进行推理☆34Updated last year
- ☆10Updated last year
- A more efficient GLM implementation!☆55Updated last year
- 想要从零开始训练一个中文的mini大语言模型,可以进行基本的对话,模型大小根据手头的机器决定☆56Updated 5 months ago
- 在kaggle部署ChatGLM API,和ChatGPT api使用相同的调用方式☆14Updated last year
- ☆43Updated 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
- XVERSE-7B: A multilingual large language model developed by XVERSE Technology Inc.☆51Updated 9 months ago
- zero零训练llm调参☆31Updated last year
- 演示 vllm 对中文大语言模型的神奇效 果☆31Updated last year
- Fastllm-based chatbot☆11Updated last year
- this repo is mnbvc text quality classification using fastText☆15Updated last year
- share data, prompt data , pretraining data☆35Updated last year
- A dataset template for guiding chat-models to self-cognition, including information about the model’s identity, capabilities, usage, limi…☆26Updated last year
- Service for Bert model to Vector. 高效的文本转向量(Text-To-Vector)服务,支持GPU多卡、多worker、多客户端调用,开箱即用。☆10Updated 2 years ago
- Graph QABot Demo| 图谱问答案例☆15Updated last year