Fix: load LFM2-VL from onnx-community repo (transformers.js layout, fp16)#19
Merged
Conversation
….js layout) with fp16 The LiquidAI -ONNX repo uses embed_images/decoder file names that the Transformers.js ImageTextToText loader cannot resolve (it requests vision_encoder/decoder_model_merged). Switch to the onnx-community repo, which follows the convention, and use fp16 (its only quantized variant; no q4). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The LiquidAI
-ONNXrepo usesembed_images/decoderfile names that the Transformers.js high-level loader can't resolve (it requestsvision_encoder/decoder_model_merged), so model loading 404'd.Switches to
onnx-community/LFM2-VL-1.6B-ONNX(conventional Transformers.js layout) and uses fp16 (its only quantized variant — no q4). WebGPU primary with WASM fallback; processor built manually fromprocessor_config.json(nopreprocessor_config.jsonin the repo).Gates: typecheck · lint · 245 tests · build all green.
🤖 Generated with Claude Code