Hugging Face's logo

bytedance-research
/
ChatTS-14B

Text Generation
Transformers
PyTorch
chatts
feature-extraction
conversational
custom_code
Model card Files Community
13

Update processing_qwen2_ts.py to allow text-only processing

#6
by alexanderchemeris - opened
base: refs/heads/main
←
from: refs/pr/6
Discussion Files changed
+8
-11
alexanderchemeris

This change is required for two purposes:

  1. Text-only inference (no timeseries input).
  2. vLLM v1 engine with prompt caching. In this case vLLM engine processes text and multimodal parts of the prompt separately.
Update processing_qwen2_ts.py to allow text-only processing4f719ca3
xiezhe24
 bytedance-research org

Thank you for fixing this!

xiezhe24 changed pull request status to merged
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment