GLM-4.6V-Flash / README.md
ericbotti's picture
Upload folder using huggingface_hub
f875127 verified
---
language:
- zh
- en
library_name: transformers
license: mit
pipeline_tag: image-text-to-text
base_model:
- zai-org/GLM-4.6V-Flash
---
# GLM-4.6V-Flash Modified Tokenizer
This is a modified version of the tokenizer for GLM-4.6V-Flash. You can find the full details for the parent model [here](https://huggingface.co/zai-org/GLM-4.6V-Flash).
## What's Changed
The chat template has been modified to preserve reasoning content (`<think>` blocks) from the previous assistant turn in addition to the current one. This creates a "rolling window" of visible thinking, allowing important thoughts to be carried forward across turns without flooding the context with tokens from all previous reasoning blocks.