Comments (14)
我测试了也是这样,没有做对话训练的结果把, 相当于其他公司的 base 模型,后期应该会有 chat 的模型
from yi.
这又不是chat模型
from yi.
这个应该是base版本模型,我这边测试发现也只是做补全,就像llama1刚放出来时那样
from yi.
这是base模型,不是chat模型,等chat模型公布在测试
from yi.
建议使用finetune代码训练之后的chat模型试一下
from yi.
这破模型,根本就不看类型,也不看自述文件,就在这胡编乱造,令人无语
from yi.
@lkp1985 单看截图,回复里多了个?
。你可以把 eos_token='\n'
去掉对比看下。
from yi.
Chat 模型已经发布,可以再试试呢? 🤗
from yi.
这破模型,根本就不看类型,也不看自述文件,就在这胡编乱造,令人无语
可以自己finetune一下
from yi.
README写了是预训练模型,不懂的话可以先友好的问一下。
from yi.
from yi.
它可以用中文写instruction,按照alpaca的格式来写,并需要给到它context定义,使用它的GPTQ版本可以较好的进行支持对话,而且是uncensored的,对中文支持也比较好,但是经常会出现回复重复的问题,中文的某些资料不全哈哈哈。
from yi.
@lkp1985 单看截图,回复里多了个
?
。你可以把eos_token='\n'
去掉对比看下。
找到问题了,是tokenizer的原因,把tokenizer=''就可以了
from yi.
它可以用中文写instruction,按照alpaca的格式来写,并需要给到它context定义,使用它的GPTQ版本可以较好的进行支持对话,而且是uncensored的,对中文支持也比较好,但是经常会出现回复重复的问题,中文的某些资料不全哈哈哈。
请问具体是如何做的呢?这样吗
[SYSTEM]{system message}[/SYSTEM]
[INST]{instructions}[/INST]
{response}
from yi.
Related Issues (20)
- 偶发性的会报错
- v100显卡,加载量化模型Yi-34B-Chat-4bits,推理速度很慢 HOT 7
- Features : openai_api.py support multi turn dialogs. HOT 1
- Result of Yi-6B-Chat on the BBH dataset cannot be reproduced HOT 1
- Yi-VL-34b支持int4量化吗?怎么操作 HOT 2
- 自定义数据train.jsonl 8万多,eval.jsonl 105条,为什么SFT时候只显示 length of train dataset:2852,length of eval dataset: 9 HOT 1
- When the API is called multiple times, the GPU memory continuously increases until it overflows. HOT 1
- LLama3发表了,啥时候Yi出新版本啊 HOT 2
- RuntimeError: "triu_tril_cuda_template" not implemented for 'BFloat16'” HOT 4
- Test issue bot
- Test issue bot
- where can I find the training code or script for YI-VL HOT 1
- lora微调yi-6b-chat之后,生成的结果会出现大量的换行符以及空格 HOT 4
- YI:9b在长上下下回答异常 HOT 5
- 用自己的数据集微调时会出现下面的报错,但是用官方的yi_example数据集就不会出现报错,请问这是为什么? HOT 1
- 请问有Yi-VL可以实现few-shot(in-context)数据的推理或微调吗? HOT 1
- Let's Build Yi Cookbook Together - Your Ideas Matter! HOT 4
- 拉了一个多模态大模型技术交流群,大家可以加入进来进行技术交流
- 📝 Yi 周边设计集思广益 HOT 1
- 🧠 Yi Merchandise Design Brainstorming!!! 🚀
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from yi.