Yudi Xue
Yudi Xue
this is exciting and would love to build on top of it. For us, we have 5 data scientists authoring workflow on airflow and I'd like to move them to...
### System Info Docker Image: ghcr.io/huggingface/text-generation-inference:sha-1734540 Instance: AWS A10G via Huggingface Interfence Endpoint ### Information - [X] Docker - [ ] The CLI directly ### Tasks - [X] An officially...
Hi my commitment has been limited for this project at the moment, I'd love to help a volunteer who would like to contribute to this project, thanks!
Hello, I was seeing warning during finetuning Mistral and tracked this line here https://github.com/huggingface/alignment-handbook/blob/main/src/alignment/model_utils.py#L71 Because Mistral's tokenizer model max length has a large number so the model_max_length set as 2048....
## Motivation Initial integration with prometheus client to facilitate metrics logging and expose the metrics to `/metrics`, which can be collected by external Grafana collectors such as alloy. [prometheus client](https://prometheus.github.io/client_python/multiprocess/)...
## Motivation I would like to be able to interpret response from reasoning models such as qwen3 and ## Modifications Added a `SglSeparateReasoning` expression, used by the `separate_resoning` API. It...