ms-agent
ms-agent copied to clipboard
MS-Agent: Lightweight Framework for Empowering Agents with Autonomous Exploration in Complex Task Scenarios
## Change Summary 1. add tool manager service module to deploy tool in a docker container, and playing as proxy to visit the tool node container 2. move all tokens...
! 请不要合并 通过replicate提供的api调用llama3-70b模型,当前已能运行。 replicate没有提供history的接口,此处还需要额外处理 
### Description    ### Link _No response_
为什么只取第0条消息,而不是把所有消息整合成 raw_prompt ```python def _chat_no_stream(self, messages: List[Dict], stop: Optional[List[str]] = None, **kwargs) -> str: # The ModelScopeLLM only supports str inputs? prompt = messages[0]['content'] if self.custom_chat and self.model.chat: response =...
### Description 1. Doc for agent about train_cn 2. Doc for agent about train_agentfabric_llm_tool_use_cn ### Link _No response_
### Description 1. Doc for agent about train_cn 2. Doc for agent about train_agentfabric_llm_tool_use_cn ### Link _No response_
按照此教程配置好环境https://github.com/modelscope/modelscope-agent/blob/master/docs/local_deploy.md,执行时tool如何调用?比如我配置这个“语音生成”的tool,远程调用api,会有如下错误。 错误日志如下 2024-03-06 17:06:43.901 - modelscope-agent - INFO - | message: using builder model qwen1.5-4b-chat | uuid: local_user | details: {} | step: | error: 2024-03-06 17:06:46,909 - modelscope -...
## Change Summary ## Related issue number ## Checklist * [ ] The pull request title is a good summary of the changes - it will be used in the...
## Change Summary 1. add docs/training_llms/train_cn.md 2. add docs/training_llms/train_agentfabric_llm_tool_use_cn.md 3. fix finetune script in train documentation, docs/training_llms/train.md 4. Update swift version in the example of finetune_llm ## Related issue number...
### Initial Checks - [X] I have searched GitHub for a duplicate issue and I'm sure this is something new - [X] I have read and followed [the docs &...