Comments (4)
Hi, we found that you were using Qwen(1.0) code to finetune Qwen1.5 models, which is incompatible. To finetune Qwen1.5 models, please refer to the README.
from qwen1.5.
I was able to make it work with the same script as 1.0 but adapted to 1.5, please advise if it's correct:
from qwen1.5.
Hi, we found that you were using Qwen(1.0) code to finetune Qwen1.5 models, which is incompatible. To finetune Qwen1.5 models, please refer to the README.
你好 请问直接添加特殊token可以吗 我看llamafactory好像是往tokenizer对象里加里特殊token?
hello,Is it possible to add special tokens in tokenizer?
from qwen1.5.
Check the latest finetuning script, or Llama factory, or Axolotl
from qwen1.5.
Related Issues (20)
- 多轮会话是否不支持工具调用 HOT 2
- vllm部署qwen如何统计token数量呢? HOT 3
- 为什么词表中文是乱码的? HOT 1
- Qwen1.5-32B-chat自己量化后问知识库相关信息,总是出现更新截止时间xx年xx月 HOT 1
- 文档中 32B 模型的benchmark数据能否补充一下
- vllm加载qwen moe gptq int4量化模型 HOT 4
- What is the number of training tokens for Qwen 1.5? With a source or official contributor if possible. HOT 1
- 使用 examples/sft目录下的脚本微调模型后,如何与原模型进行融合 HOT 2
- 2.0开源快了吧 HOT 1
- qwen moe 推理速度非常慢 HOT 2
- 32BAWQ 4张4090很快,换8张很慢很慢
- 请问训练或者推理时如何自定义修改每个时间步的causal mask? HOT 1
- Qwen1.5-72B-Chat发送function角色消息时抛错 HOT 1
- VLLM部署Qwen1.5-32B-Chat-GPTQ-Int4,总是说CUDA out of memory,但实际cuda内存是足够的 HOT 1
- qwen1.5-110B lora微调结果有问题,不能正常结束
- 是否可以输入表格的html信息进行信息提取,类似将文本做成markdown格式输入?promt如何设置呢?
- 是否存在保留的特殊token HOT 1
- 通过vllm部署Qwen1.5-14B后,模型推理能力急剧下降 HOT 1
- Qwen1.5-7B使用推荐用法脚本运行,对提问的回答会带有其他莫名的问答数据 HOT 2
- Qwen1.5-32B-chat模型在高并发下相同prompt且温度为0会返回多样性应答 HOT 2
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 qwen1.5.