Image-Text-to-Text
LiteRT-LM
LiteRT
litertlm
on-device
vision-language
object-detection
referring-expression-comprehension
object-counting
point-grounding
ocr
Instructions to use litert-community/WeVisOne-VL-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use litert-community/WeVisOne-VL-4B with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli # A single .litertlm file in the repo is picked automatically; otherwise the CLI asks which one to run # (or pass its name right after the repo id). litert-lm run \ --from-huggingface-repo=litert-community/WeVisOne-VL-4B \ --prompt="Write me a poem"
- LiteRT
How to use litert-community/WeVisOne-VL-4B with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Commit History
5 days ago
-
Card and MEASUREMENTS.md: benchmark prefill counts are no longer called prompt lengths
Verified signatureREADME.md: - In benchmark mode the number of tokens to prefill is a setting (1,024). The card called that number a prompt length; it now says "prefill". MEASUREMENTS.md: - In benchmark mode the number of tokens to prefill is a setting (1,024). The file called that number a prompt length; it now says "prefill".b509dff
8 days ago
-
Mac rows for the files of 2026-11-12 (Apple M4 Max, LiteRT-LM 0.19.1: the int4 file on the GPU and the CPU, the int8 file on the CPU) in the card, MEASUREMENTS.md and litertlm_manifest.json
Verified signatured0d8d73 -
litertlm_manifest.json: both files with external weights (sha256, size, sections), min_runtime_version 0.19.0, the LiteRT-LM#3986 line
Verified signature96c44fd -
Both files with LiteRT external weights (the same weights; an Android GPU needs LiteRT-LM 0.19.0 or later, the earlier files stay at revision ee03d010); card and MEASUREMENTS updated
Verified signatureb4ed353
9 days ago
-
Correct three details in the card and MEASUREMENTS.md and make their wording clearer
Verified signatureee03d01
10 days ago
-
Add WeVisOne-VL-4B_int8.litertlm, the file for a CPU, with its card rows, measurements and manifest entry
Verified signaturef8ca054 -
Card: the Android library run of a test app, this file against an int8 variant for the GPU in turns (2026-11-10), process count
Verified signature872c152 -
Card: shorter card; how the numbers were measured, raw values and earlier runs moved to MEASUREMENTS.md
Verified signature2fcc2c1 -
Card: library path, prompt file, cache files and how build B was made
Verified signature90d80c1 -
Add WeVisOne-VL-4B int4 LiteRT-LM file, model card and manifest
Verified signaturecfe3cff -
initial commit
Verified signature0e6d6d6