Feature Extraction
Transformers
Safetensors
lfm2
fill-mask
encoder-only
multimodal
image-text-retrieval
image-text-matching
siglip2
lfm2.5
gptq
custom_code
compressed-tensors
Instructions to use konic-labs/LFM2.5-multimodal-encoder-230M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use konic-labs/LFM2.5-multimodal-encoder-230M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="konic-labs/LFM2.5-multimodal-encoder-230M", trust_remote_code=True)# Load model directly from transformers import AutoTokenizer, AutoModelForMaskedLM tokenizer = AutoTokenizer.from_pretrained("konic-labs/LFM2.5-multimodal-encoder-230M", trust_remote_code=True) model = AutoModelForMaskedLM.from_pretrained("konic-labs/LFM2.5-multimodal-encoder-230M", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| default_stage: | |
| default_modifiers: | |
| GPTQModifier: | |
| targets: [Linear] | |
| ignore: ['re:.*lm_head'] | |
| scheme: W4A16 | |
| bypass_divisibility_checks: false | |
| requires_calibration_data: true | |
| block_size: 128 | |
| dampening_frac: 0.01 | |
| actorder: static | |
| offload_hessians: false | |