Comments (6)
junjzhang
commented on June 3, 2024
1
@mzh1996 我解决了，在请求时使用 skip_special_tokens=False
from qwen1.5.
JustinLin610
commented on June 3, 2024
参考readme的用例，直接使用vllm，要用apply_chat_template给输入封上chatml格式
from qwen1.5.
mzh1996
commented on June 3, 2024
apply_chat_template
感谢
from qwen1.5.
junjzhang
commented on June 3, 2024
@mzh1996 请问你\n\n\n问题解决了吗，我在vllm中使用了chatml的template还是会有这个问题
from qwen1.5.
mzh1996
commented on June 3, 2024
@mzh1996 请问你\n\n\n问题解决了吗，我在vllm中使用了chatml的template还是会有这个问题
@junjzhang 暂时没解决，我觉得我还是没成功套上chatml模板
from qwen1.5.
mzh1996
commented on June 3, 2024
@junjzhang 牛的，不过感觉可能咱们用的方式还是不对（比如template的加载），按理来说不应该这样的。我尝试硬在prompt构造时加上You are a helpful assistant的那个模板，效果改善不少
from qwen1.5.
Related Issues (20)
- qwen1.5-72b支持输入和输出的tokens是多大？ HOT 3
- 有计划适配unsloth吗？
- 在执行示例代码时输出乱码 HOT 2
- Qwen1.5-0.5B-Chat推理的时候出现：RuntimeError: Expected all tensors to be on the same device, but found at least two devices, cuda:7 and cpu! (when checking argument for argument index in method wrapper__index_select) HOT 5
- Qwen/CodeQwen1.5-7B-Chat "model_max_length": 1000000000000000019884624838656," ? HOT 3
- [Question]Preprocess function: target_ids did not mask the prompt section. HOT 1
- 6张卡，怎么能够让vllm启动qwen1.5-32b-chat
- 请问官网dashscope中的qwen1.5-14b-chat支持调用tools功能吗？ HOT 2
- 标准prompt，在Qwen1.5-MoE-A2.7B解析错误，在Qwen1.5 7b chat解析正确，该如何调整 ? HOT 3
- Force English Output HOT 2
- 请问一下模型后缀instruct，base，chat 该怎么选？ HOT 1
- Qwen1.5-7B-Chat AWQ量化的MMLU评测效果相比Qwen1.5-7B-Chat-GPTQ-Int4和Qwen1.5-7B-Chat相差特别大 HOT 3
- 多卡训练报错：ImportError: /root/.cache/torch_extensions/py38_cu118/fused_adam/fused_adam.so: cannot open shared object file: No such file or directory HOT 1
- Qwen1.5-110B-Chat-GPTQ-Int4模型在system提示词中加入引号或者换行会导致模型不输出 HOT 1
- Qwen1.5-110B-Chat的中文能力是否评测过，如cmmlu，ceval等 HOT 2
- Qwen1.5-72B-Chat-GPTQ-Int4 能否在4*16G V100上跑起来？ HOT 3
- Qwen/Qwen1.5-110B-Chat-AWQ can't run successfully, until I replace the 110B's **tokenizer_config.json** with 70B's HOT 2
- 求微调建议：微调后的7B-chat模型推理的效果极差
- 求微调建议：微调后的7B-chat模型推理的效果极差 HOT 5
- Qwen1.5 110b AWQ终止符问题 HOT 3
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.