-
**问题描述 / Problem Description**
执行`chatchat-kb -r`报错
**复现问题的步骤 / Steps to Reproduce**
1. 执行 `chatchat-kb -r`
**预期的结果 / Expected Result**
初始化数据库成功
**实际结果 / Actual Result**
报错
```
2024…
-
CPU-only reference on Xiaomi 14.
here is a screenshot to demonstrate this issue(the input question is: where is China's capital city?):
![264844392](https://github.com/zhouwg/kantv/assets/68899…
-
看了训练流程图,我理解这个对齐器是不是在全参微调,我跑百川7b的模型,4090 24G的显卡,跑不起来,显存满了,只能换更大的显存吗?多大的显存合适?
![image](https://github.com/Aligner2024/aligner/assets/18018532/00560305-a808-4ca8-9ec1-9faea2ba6daf)
-
Server crashes when I'm trying to run llama.cpp bench.
Steps to reproduce:
1) git clone https://github.com/ggerganov/llama.cpp.git
2) build llama.cpp via Vulkan support according to https://git…
-
When using the Vulkan backend on the llama-3-8B platform and nearly saturating the VRAM ( 7.8/7.98 with a 16k context ), the generated output becomes gibberish, often consisting of repeated letters. T…
-
### 起始日期 | Start Date
_No response_
### 实现PR | Implementation PR
_No response_
### 相关Issues | Reference Issues
_No response_
### 摘要 | Summary
vllm支持Qwen1.5-14B-Chat-AWQ和Qwen1.5-14B-Chat-GPTQ-in…
-
latest llama cpp output incoherently compare to Transformers output.
transformers/vllm work ok but llama cpp gguf does not
-
Thanks for your code. I encountered the following issue while trying to extend the context length of Qwen1.5-14B-Chat. Do you know how I can fix this Exception? Many THX!
```python
Traceback (most…
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
## 微调参数及输出
```text
llamafactory-cli train \
--stage sft \
--do_train \
--model_name_or_…
-
### Describe the bug
docker部署时:Unexpected error from cudaGetDeviceCount(),容器能跑起来,但是模型不能在GPU中跑起来,只能跑在内存里
### To Reproduce
docker容器启动日志:
```
2024-06-23 06:16:01,661 xinference.core.supervisor 59 …