-
All config are default, nothing changed after git clone and habor installation steps.
I am using ollama instance running outside of docker (not the harbor ollama), which can be accessed by webui when…
-
-
**问题描述 / Problem Description**
无法找到xinference中自定义的模型，并且提问出错
**复现问题的步骤 / Steps to Reproduce**
1. 执行 'xinference-local --host 0.0.0.0 --port 9997' 启动 xinference， 注册了 `bge-large-zh-lacal` 和 `glm4-lo…
kydbj updated
2 months ago
-
### Reminder
- [X] I have read the README and searched the existing issues.
### Reproduction
CUDA_VISIBLE_DEVICES=0 \
USE_MODELSCOPE_HUB=1 \
API_PORT=7860 \
python src/api_demo.py \
--model…
-
### Feature request
目前，paddlenlp 的大模型问答功能仅支持单轮问答。为了充分发挥大型语言模型的潜力，建议增强其对话功能，支持多轮对话、agent对话和工具对话。同时，当前的设计将命令行和业务组件混合在一起，建议明确命令行负责启动接口，代码负责实现业务组件，以提升代码的可维护性和扩展性。
当前实现:
python
复制代码
from paddlenlp…
-
File "core/folotoy_app.py", line 126, in core.folotoy_app.FolotoyApp.start
File "/usr/local/lib/python3.11/site-packages/paho/mqtt/client.py", line 914, in connect
return self.reconnect()
…
-
Right now, completions code relies on the ollama /api/generate endpoint. This means we need to use ollama, which is good but also limits applicability.
I would like to be able to use either the /v1…
-
### 是否已有关于该错误的issue或讨论？ | Is there an existing issue / discussion for this?
- [X] 我已经搜索过已有的issues和讨论 | I have searched the existing issues / discussions
### 该问题是否在FAQ中有解答？ | Is there an existing…
-
Is there a mistake of the action space "grab" , the description in the document seem to be wrong?
**bool. If True and the agent is holding an object, grab the object at the center of the image. If Tr…
-
### What is the issue?
Running `ollama run mistral ""& /set nohistory & /set quiet &` in a bash script as the entrypoint to a docker container, in an attempt to start mistral right after starting the…