-
I understand that mistral and deepseek will be supported soon, but for instruction following Qwen 2.5 is actually better. So can we pretty please to add support for Qwen 2.5-72b-instruct model as well…
-
Hi!
Does trtllm support https://huggingface.co/deepseek-ai/deepseek-moe-16b-base ? Do you have any plans to support?
-
### Your current environment
```text
Collecting environment information...
PyTorch version: 2.3.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
…
zxdvd updated
2 weeks ago
-
### 📦 部署方式
Other
### 📌 软件版本
最新
### 💻 系统环境
Windows
### 📌 系统版本
win 10
### 🌐 浏览器
Chrome
### 📌 浏览器版本
最新版127.0.6533.100
### 🐛 问题描述
地址尝试了https://api.deepseek.com/v1、https://api.deepseek.com/
模…
-
### Describe the bug
when using any other llm than Sonnet 3.5 i get nothing in the Preview window no matter how many times i prompt the bloddy thing. Gemini, Deepseek, 4o none can give me a preview…
-
RuntimeError: CUDA error: an illegal memory access was encountered
Looking forward to the expert's answer
-
模型转换前后大小差别很大（30G->53G)，是存在什么问题吗
-
### Which API Provider are you using?
OpenAI Compatible
### Which Model are you using?
o1-mini
### What happened?
o1 series model available
### Steps to reproduce
![image](https://github.com/us…
-
## Describe the bug
Identical useless output on inputs for deepseek-coder-v2:16b-lite-base-q4_0
## How to reproduce
Use deepseek-coder-v2:16b-lite-base-q4_0 through ollama, type:
```
#inc…
-
: invalid vectorizer config: model not found at '/var/www/models/bge-m3', nor model url specified
配置文件：
namespace = KagDemo
host_addr = http://localhost:8887
id = 1
[vectorizer]
vectorizer =…