-
### Your current environment
I'm encountering an AssertionError when trying to load the Qwen 2.5 GGUF (Qwen-2.5-q3_gguf.bin) model using vLLM. The error occurs in the vocab_parallel_embedding.py file…
-
### 前置确认
- [X] 我确认我运行的是最新版本的代码,并且安装了所需的依赖,在[FAQS](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs)中也未找到类似问题。
### ⚠️ 搜索issues中是否已存在类似问题
- [X] 我已经搜索过issues和disscussions,没有跟我遇到的问题相关的issue
###…
-
```
llm_cfg = {
# Use the model service provided by DashScope:
'model': 'qwen-vl-max-0809',
#'api_key': 'YOUR_DASHSCOPE_API_KEY',
# It will use the `DASHSCOPE_API_KEY' environment…
-
I am using the qwen 72B model, and the specified --conv-template does not take effect. If the stop parameter is not specified when calling, the conversation will never end.
启动命令
```
CUDA_VISIBLE_…
-
## 第一步:创建一个名为 `docker-compose.yml` 的文件,并填入以下内容:
> 注意:
> 1. `YOUR_DASHSCOPE_API_KEY` 需要替换为你自己的[通义千问的 API Key](https://help.aliyun.com/zh/dashscope/opening-service?spm=a2c4g.11186623.0.0.72c2369dLpr…
-
I use a third party compatible with the OpenAI API to enable the Qwen model, but cross-domain needs to be enabled, otherwise it will not work properly.
我使用兼容OpenAI API的第三方可以启用通义千问模型,但是需要开启跨域,否则无法正常…
-
### 📦 部署环境
Other
### 📌 软件版本
v1.5.1
### 💻 系统环境
Windows, iOS
### 🌐 浏览器
Edge, Safari
### 🐛 问题描述
目前部署在Azure北美容器应用上,一直存在类似 #3108 的问题,但早期无论是否打开客户端请求模式都存在问题。目前最新版本v1.5.1已默认关闭客户端请求模…
-
Hello,
First of all thank you for bringing this amazing tool! I was wondering if there is any chance of integrating open-source LMM models like for example https://huggingface.co/Qwen/Qwen2-VL-7B-…
-
目前能否支持Gemini自定义接口地址?
Spark和Qwen自定义接口存在以下报错:
```Spark
malformed ws or wss URL
```
```Qwen
Unmarshal response body failed,err:"Syntax error at index 1: invalid char\n\n\t\n\n\t.^............…
-
### Proposal to improve performance
_No response_
### Report of performance regression
INFO 09-11 12:41:50 spec_decode_worker.py:790] SpecDecodeWorker stage times: average_time_per_proposal_t…