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 # Warning: Pipeline type "visual-question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("visual-question-answering", model="openbmb/OmniLMM-12B")# pip install -U transformers accelerate # Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("openbmb/OmniLMM-12B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download special_tokens_map.json from openbmb/OmniLMM-12B: direct link, hf CLI and curl.
- Browser
- Download file 759 Bytes
-
https://huggingface.co/openbmb/OmniLMM-12B/resolve/main/special_tokens_map.json
- Command line
-
hf download hf://openbmb/OmniLMM-12B/special_tokens_map.json
-
curl -L -o special_tokens_map.json https://huggingface.co/openbmb/OmniLMM-12B/resolve/main/special_tokens_map.json
759 Bytes
| { | |
| "additional_special_tokens": [ | |
| "<unk>", | |
| "<s>", | |
| "</s>", | |
| "<im_patch>", | |
| "<im_start>", | |
| "<im_end>", | |
| "<box>", | |
| "</box>", | |
| "<ref>", | |
| "</ref>", | |
| "<quad>", | |
| "</quad>" | |
| ], | |
| "bos_token": { | |
| "content": "<s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "eos_token": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "pad_token": { | |
| "content": "</s>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| }, | |
| "unk_token": { | |
| "content": "<unk>", | |
| "lstrip": false, | |
| "normalized": false, | |
| "rstrip": false, | |
| "single_word": false | |
| } | |
| } | |