20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Doc] Explicitly state that InternVL 2.5 is supported (#10978)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2024-12-08 00:58:02 +08:00 committed by GitHub
parent bf0e382e16
commit 1c768fe537
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
docs/source/models/supported_models.rst
View File

@ -547,9 +547,9 @@ Text Generation
- ✅︎ - ✅︎
- -
* - :code:`InternVLChatModel` * - :code:`InternVLChatModel`
- InternVL2 - InternVL 2.5, Mono-InternVL, InternVL 2.0
- T + I\ :sup:`E+` - T + I\ :sup:`E+`
- :code:`OpenGVLab/Mono-InternVL-2B`, :code:`OpenGVLab/InternVL2-4B`, :code:`OpenGVLab/InternVL2-8B`, etc. - :code:`OpenGVLab/InternVL2_5-4B`, :code:`OpenGVLab/Mono-InternVL-2B`, :code:`OpenGVLab/InternVL2-4B`, etc.
- -
- ✅︎ - ✅︎
* - :code:`LlavaForConditionalGeneration` * - :code:`LlavaForConditionalGeneration`

2
examples/offline_inference_vision_language.py
View File

@ -223,7 +223,7 @@ def run_internvl(question: str, modality: str):
# Stop tokens for InternVL # Stop tokens for InternVL
# models variants may have different stop tokens # models variants may have different stop tokens
# please refer to the model card for the correct "stop words": # please refer to the model card for the correct "stop words":
# https://huggingface.co/OpenGVLab/InternVL2-2B#service # https://huggingface.co/OpenGVLab/InternVL2-2B/blob/main/conversation.py
stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"] stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"]
stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens] stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]
return llm, prompt, stop_token_ids return llm, prompt, stop_token_ids

2
examples/offline_inference_vision_language_multi_image.py
View File

@ -165,7 +165,7 @@ def load_internvl(question: str, image_urls: List[str]) -> ModelRequestData:
# Stop tokens for InternVL # Stop tokens for InternVL
# models variants may have different stop tokens # models variants may have different stop tokens
# please refer to the model card for the correct "stop words": # please refer to the model card for the correct "stop words":
# https://huggingface.co/OpenGVLab/InternVL2-2B#service # https://huggingface.co/OpenGVLab/InternVL2-2B/blob/main/conversation.py
stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"] stop_tokens = ["<|endoftext|>", "<|im_start|>", "<|im_end|>", "<|end|>"]
stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens] stop_token_ids = [tokenizer.convert_tokens_to_ids(i) for i in stop_tokens]