hahmad2008

Results 43 comments of hahmad2008
trafficstars

[Bug]: Deepseek resoning content is coming as null and the think content is going inside content when using vllm-openai v0.7.2 docker containers

@Nietism can you share the chat template you used? or the change you did? can't get this revision `--tokenizer-revision 6453600843497f04e63f069049e92bf221d9e000`

[Bug]: Deepseek resoning content is coming as null and the think content is going inside content when using vllm-openai v0.7.2 docker containers

@Nietism @majestichou I tried this chat template and now I can see the reasoning content, however I there is `\n` `\n\n` in the beginning of the reasoning content and the...

How to serve local models with python package (not docker)

@nbroad1881 If I install TGI from the source, then can I run it for local or ay HF models?