Add/update the quantized ONNX model files and README.md for Transformers.js v3

by whitphx HF Staff - opened 24 days ago

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

+60

-0

whitphx

24 days ago

Applied Quantizations

✅ Based on `decoder_model.onnx` with slimming

↳ ✅ fp16: decoder_model_fp16.onnx (added)
↳ ✅ int8: decoder_model_int8.onnx (added)
↳ ✅ uint8: decoder_model_uint8.onnx (added)
↳ ✅ q4: decoder_model_q4.onnx (added)
↳ ✅ q4f16: decoder_model_q4f16.onnx (added)
↳ ✅ bnb4: decoder_model_bnb4.onnx (added)

✅ Based on `decoder_with_past_model.onnx` with slimming

↳ ✅ fp16: decoder_with_past_model_fp16.onnx (added)
↳ ✅ int8: decoder_with_past_model_int8.onnx (added)
↳ ✅ uint8: decoder_with_past_model_uint8.onnx (added)
↳ ✅ q4: decoder_with_past_model_q4.onnx (added)
↳ ✅ q4f16: decoder_with_past_model_q4f16.onnx (added)
↳ ✅ bnb4: decoder_with_past_model_bnb4.onnx (added)

❌ Based on `decoder_model_merged.onnx` with slimming

The base model decoder_model_merged.onnx has been renamed to model.onnx.

None

↳ ❌ fp16: `` (added but JS-based E2E test failed)

[0;93m2025-08-29 07:17:35.684735812 [W:onnxruntime:, graph.cc:113 MergeShapeInfo] Error merging shape info for output. '/transformer/Slice_output_0' source:{2} target:{1}. Falling back to lenient merge.[m
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25
            __classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
                                                                                           ^

Error: Load model from /tmp/tmp8a26ml89/c1d88f6743334a1200e4948ef46f545acfa96568/onnx/model_fp16.onnx failed:Node (/transformer/Squeeze) Op (Squeeze) [ShapeInferenceError] Dimension of input 0 must be 1 instead of 2
    at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25:92)
    at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:67:29)
    at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0

↳ ❌ int8: `` (added but JS-based E2E test failed)

[0;93m2025-08-29 07:17:46.341049068 [W:onnxruntime:, graph.cc:113 MergeShapeInfo] Error merging shape info for output. '/transformer/Slice_output_0' source:{2} target:{1}. Falling back to lenient merge.[m
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25
            __classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
                                                                                           ^

Error: Load model from /tmp/tmp8a26ml89/c1d88f6743334a1200e4948ef46f545acfa96568/onnx/model_int8.onnx failed:Node (/transformer/Squeeze) Op (Squeeze) [ShapeInferenceError] Dimension of input 0 must be 1 instead of 2
    at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25:92)
    at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:67:29)
    at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0

↳ ❌ uint8: `` (added but JS-based E2E test failed)

[0;93m2025-08-29 07:17:57.546248750 [W:onnxruntime:, graph.cc:113 MergeShapeInfo] Error merging shape info for output. '/transformer/Slice_output_0' source:{2} target:{1}. Falling back to lenient merge.[m
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25
            __classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
                                                                                           ^

Error: Load model from /tmp/tmp8a26ml89/c1d88f6743334a1200e4948ef46f545acfa96568/onnx/model_uint8.onnx failed:Node (/transformer/Squeeze) Op (Squeeze) [ShapeInferenceError] Dimension of input 0 must be 1 instead of 2
    at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25:92)
    at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:67:29)
    at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0

↳ ❌ q4: `` (added but JS-based E2E test failed)

[0;93m2025-08-29 07:18:06.398696360 [W:onnxruntime:, graph.cc:113 MergeShapeInfo] Error merging shape info for output. '/transformer/Slice_output_0' source:{2} target:{1}. Falling back to lenient merge.[m
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25
            __classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
                                                                                           ^

Error: Load model from /tmp/tmp8a26ml89/c1d88f6743334a1200e4948ef46f545acfa96568/onnx/model_q4.onnx failed:Node (/transformer/Squeeze) Op (Squeeze) [ShapeInferenceError] Dimension of input 0 must be 1 instead of 2
    at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25:92)
    at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:67:29)
    at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0

↳ ❌ q4f16: `` (added but JS-based E2E test failed)

[0;93m2025-08-29 07:18:12.608451741 [W:onnxruntime:, graph.cc:113 MergeShapeInfo] Error merging shape info for output. '/transformer/Slice_output_0' source:{2} target:{1}. Falling back to lenient merge.[m
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25
            __classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
                                                                                           ^

Error: Load model from /tmp/tmp8a26ml89/c1d88f6743334a1200e4948ef46f545acfa96568/onnx/model_q4f16.onnx failed:Node (/transformer/Squeeze) Op (Squeeze) [ShapeInferenceError] Dimension of input 0 must be 1 instead of 2
    at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25:92)
    at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:67:29)
    at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0

↳ ❌ bnb4: `` (added but JS-based E2E test failed)

[0;93m2025-08-29 07:18:21.406956044 [W:onnxruntime:, graph.cc:113 MergeShapeInfo] Error merging shape info for output. '/transformer/Slice_output_0' source:{2} target:{1}. Falling back to lenient merge.[m
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25
            __classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
                                                                                           ^

Error: Load model from /tmp/tmp8a26ml89/c1d88f6743334a1200e4948ef46f545acfa96568/onnx/model_bnb4.onnx failed:Node (/transformer/Squeeze) Op (Squeeze) [ShapeInferenceError] Dimension of input 0 must be 1 instead of 2
    at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:25:92)
    at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/onnxruntime-node@1.21.0/node_modules/onnxruntime-node/dist/backend.js:67:29)
    at process.processImmediate (node:internal/timers:485:21)

Node.js v22.16.0

Add/update the quantized ONNX model files and README.md for Transformers.js v3ed9213ea

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Ready to merge

This branch is ready to get merged automatically.

· Sign up or log in to comment

Add/update the quantized ONNX model files and README.md for Transformers.js v3

Applied Quantizations

✅ Based on decoder_model.onnx with slimming

✅ Based on decoder_with_past_model.onnx with slimming

❌ Based on decoder_model_merged.onnx with slimming

✅ Based on `decoder_model.onnx` with slimming

✅ Based on `decoder_with_past_model.onnx` with slimming

❌ Based on `decoder_model_merged.onnx` with slimming