AntX-13B
This is an experimental product that can be used to create new LLM bassed on Chinese language. —...
This is an experimental product that can be used to create new LLM bassed on Chinese language. —...
This is an experimental product that can be used to create new LLM bassed on Chinese language. —...
> Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions. However,...
> 由于LLaMA权重的许可限制,该模型不能用于商业用途,请严格遵守LLaMA的使用政策。 考虑到 ограничения лицензии на веса LLaMA, мы не можем напрямую публиковать полные веса модели. 因此,我们使用了FastChat开源工具作为基础,并对其进行了进一步的优化。 我们计算并发布了Ziya-LLaMA-13B-v1权重与原始LLaMA权重之间的差值。...
基于tigerbot-7b-sft,使用QLoRA,在medical-qa数据上微调的模型。 如果下载过tigerbot-7b-sft,可以只下载qlorackpt2400adaptermodel后合成。 Модальности:Генерация текста Области применения:Медицина Задача: Генерация текста Автор: TigerResearch Теги: bloom, medical, zh, text-generation-inference, endpoints_compatibleЛайков: 2...
使用LLaMA格式保存的baichuan-7B。可以直接使用LlamaForCausalLM和LlamaTokenizer加载。 权重文件以405M的尺寸分片,方便并行快速下载。权重来自fireballoon/baichuan-llama-7b baichuan-7B model saved in the format of the LLaMA model. You can directly use LlamaForCausalLM and...
The weight file is split into chunks with a size of 405M for convenient and fast parallel downloads...
lora:https://huggingface.co/ziqingyang/chinese-alpaca-lora-13b 将Pygmalion-13b与chinese-alpaca-lora-13b进行合并,增强模型的中文能力,~~不过存在翻译腔~~ 兼容AutoGPTQ和GPTQ-for-LLaMa 若选择GPTQ-for-LLaMa加载,请设置 Wbits=4 groupsize=128 modeltype=llama** Text-generation-webui懒人包: https://www.bilibili.com/read/cv23495183 Original model: https://huggingface.co/TehVenom/Pygmalion-13b-Merged lora:https://huggingface.co/ziqingyang/chinese-alpaca-lora-13b The Pygmalion-13b model is combined...
原始模型:https://huggingface.co/Neko-Institute-of-Science/pygmalion-7b lora:https://huggingface.co/ziqingyang/chinese-alpaca-lora-7b 将pygmalion-7b与chinese-alpaca-lora-7b进行合并,增强模型的中文能力,~~不过存在翻译腔~~ 兼容AutoGPTQ和GPTQ-for-LLaMa 若选择GPTQ-for-LLaMa加载,请设置 Wbits=4 groupsize=128 modeltype=llama** Text-generation-webui懒人包: https://www.bilibili.com/read/cv23495183 Original model: https://huggingface.co/TheBloke/Wizard-Vicuna-13B-Uncensored-HF lora:https://huggingface.co/ziqingyang/chinese-alpa Usage projects: https://github.com/ymcui/Chinese-LLaMA-Alpaca Compatible...
1. 使用了大概几万条的数据,对falcon-7b模型做了sft,这里分享出我的模型权重 2. falcon-7b是支持中文语言的。 1. 效果其实一般,没有bloom-7b效果好。有人甚至反映,连bloom-1b都干不过。 2. Здесь я делюсь весами своей модели bloom-7b-v2 https://huggingface.co/yuanzhoulvpi/chinesebloom7bchatv2 1. Модель falcon-7b...