Instructions to use openbmb/OmniLMM-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openbmb/OmniLMM-12B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("visual-question-answering", model="openbmb/OmniLMM-12B")# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("openbmb/OmniLMM-12B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download added_tokens.json from openbmb/OmniLMM-12B: direct link, hf CLI and curl.
- Browser
- Download file 183 Bytes
-
https://huggingface.co/openbmb/OmniLMM-12B/resolve/main/added_tokens.json
- Command line
-
hf download hf://openbmb/OmniLMM-12B/added_tokens.json
-
curl -L -o added_tokens.json https://huggingface.co/openbmb/OmniLMM-12B/resolve/main/added_tokens.json
183 Bytes
| { | |
| "</box>": 32004, | |
| "</quad>": 32008, | |
| "</ref>": 32006, | |
| "<box>": 32003, | |
| "<im_end>": 32002, | |
| "<im_patch>": 32000, | |
| "<im_start>": 32001, | |
| "<quad>": 32007, | |
| "<ref>": 32005 | |
| } | |