NeoAnd/Dolphin
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update doc

Browse Source
This commit is contained in:
yingdong.han 2025-06-30 19:56:25 +08:00
parent cab9b3f952
commit f171021615
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
deployment/tensorrt_llm/ReadMe.md
View File

@ -4,7 +4,7 @@
## ✅ Introduction
The Dolphin model employs a **Swin Encoder + MBart Decoder** architecture. In the HuggingFace Transformers [Config](https://huggingface.co/ByteDance/Dolphin/blob/main/config.json),
its architectures field is specified as "VisionEncoderDecoderModel". Dolphin, Nougat, and Donut share the same model architecture. TensorRT-LLM has already supported the Nougat model.
its architectures field is specified as "VisionEncoderDecoderModel". **Dolphin**, **[Nougat](https://huggingface.co/docs/transformers/model_doc/nougat)**, and **[Donut](https://huggingface.co/docs/transformers/model_doc/donut)** share the same model architecture. TensorRT-LLM has already supported the Nougat model.
Following Nougat's conversion script, we have successfully implemented Dolphin on TensorRT-LLM.
**Note:** [prompt_ids](./dolphin_runner.py#L120) MUST be of **int32** type, otherwise TensorRT-LLM will produce incorrect results.