seanzhang-zhichen

Results 16 comments of seanzhang-zhichen

> 同样遇到这个问题,只能降级使用 降级就不能和其他模型一起用了,比如说话者识别,标点恢复

i has same problem...how to solve it? please help me:

> Hey, @seanzhang-zhichen! > > Please add some details to this issue: > > * What would you like to do? What is your use case? > * Can you...

mycode: ```python from haystack.nodes import PromptNode, PromptTemplate, AnswerParser, BM25Retriever, PromptModel from haystack.pipelines import Pipeline from haystack.utils import print_answers from haystack.agents import Tool from haystack.nodes.prompt.invocation_layer.open_ai import OpenAIInvocationLayer # model = "Qwen-72B-Chat-Int4"...

Agent custom-at-query-time started with {'query': 'tell me seven wonders of the world', 'params': None} Maximum number of iterations (8) reached for query (tell me seven wonders of the world). Increase...

> The error does not seem related to a problem in contacting the endpoint. You can try increasing the max number of iterations ([`max_steps`](https://docs.haystack.deepset.ai/reference/agent-api#agent__init__)) and see what happens. Can you...

> Downgrading fschat==0.2.36 to fschat==0.2.26 resolved this issue. I guess it is caused by Qwen's tokenizer unuseful

> > 对于中文句子,每个字符后添加空格,是不是意味着截断字符最大为256? > > 是的。 那我的场景是512个字符,这个模型岂不是作用不大

> > > > 对于中文句子,每个字符后添加空格,是不是意味着截断字符最大为256? > > > > > > > > > 是的。 > > > > > > 那我的场景是512个字符,这个模型岂不是作用不大 > > 是的,可以使用其他的一些关系抽取的方法。 我看了下其他人的实现,如果没有单个实体token的问题,是可以不加空格的?

再请教下,我的业务场景实体是固定的,简单来说业务场景为根据张三李四两人的聊天记录判断谁是父亲,谁是儿子(假如是父子关系),这时实体其实是固定的,就是张三李四两人的名字,您觉得哪个模型会对这种场景的效果好一点?