[VLM][Model] Support image input for Chameleon (#6633)

This commit is contained in:
Roger Wang
2024-07-22 23:50:48 -07:00
committed by GitHub
parent c5201240a4
commit 22fa2e35cb
7 changed files with 696 additions and 58 deletions

View File

@@ -182,6 +182,10 @@ Vision Language Models
- Models
- Example HuggingFace Models
- :ref:`LoRA <lora>`
* - :code:`ChameleonForConditionalGeneration`
- Chameleon
- :code:`facebook/chameleon-7b` etc.
-
* - :code:`FuyuForCausalLM`
- Fuyu
- :code:`adept/fuyu-8b` etc.