Add/update the quantized ONNX model files and README.md for Transformers.js v3
#1
by
whitphx
HF Staff
- opened
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_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 encoder_model.onnx with slimming
None
↳ ❌ int8: encoder_model_int8.onnx (added but JS-based E2E test failed)
dtype not specified for "decoder_model_merged". Using the default dtype (fp32) for this device (cpu).
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25
__classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
^
Error: Could not find an implementation for ConvInteger(10) node with name '/embeddings/patch_embeddings/projection/Conv_quant'
at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25:92)
at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:67:29)
at process.processImmediate (node:internal/timers:485:21)
Node.js v22.16.0
↳ ✅ uint8: encoder_model_uint8.onnx (added)
↳ ✅ q4: encoder_model_q4.onnx (added)
↳ ✅ q4f16: encoder_model_q4f16.onnx (added)
↳ ✅ bnb4: encoder_model_bnb4.onnx (added)
❌ Based on encoder_model.onnx with slimming
None
↳ ❌ int8: encoder_model_int8.onnx (added but JS-based E2E test failed)
dtype not specified for "decoder_model_merged". Using the default dtype (fp32) for this device (cpu).
/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25
__classPrivateFieldGet(this, _OnnxruntimeSessionHandler_inferenceSession, "f").loadModel(pathOrBuffer, options);
^
Error: Could not find an implementation for ConvInteger(10) node with name '/embeddings/patch_embeddings/projection/Conv_quant'
at new OnnxruntimeSessionHandler (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:25:92)
at Immediate.<anonymous> (/home/ubuntu/src/tjsmigration/node_modules/.pnpm/[email protected]/node_modules/onnxruntime-node/dist/backend.js:67:29)
at process.processImmediate (node:internal/timers:485:21)
Node.js v22.16.0
↳ ✅ uint8: encoder_model_uint8.onnx (added)
↳ ✅ q4: encoder_model_q4.onnx (added)
↳ ✅ q4f16: encoder_model_q4f16.onnx (added)
↳ ✅ bnb4: encoder_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_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
0%| | 0/1 [00:00<?, ?it/s]
Processing /tmp/tmpv07qia3n/decoder_model_merged.onnx: 0%| | 0/1 [00:00<?, ?it/s]
0%| | 0/6 [00:00<?, ?it/s][A
- Quantizing to fp16: 0%| | 0/6 [00:00<?, ?it/s][A/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.118331205418599e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.765334793432885e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.830656206271215e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.0533679645495795e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.812860746194474e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.51695454980927e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.398719053559489e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.744606840745291e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.874542807760008e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.991577177790532e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.6169927376004125e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.32548752371531e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.2703192093540565e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.385328994909287e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.711802338239977e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.634087140218071e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.2646148834535325e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.9225204296353695e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.92422830184114e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.8164746030133756e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.606542430314221e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.952910094222716e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.9804627654783644e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.322649888559681e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.7261572999037753e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.9852429034017405e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.5895302286093056e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.320770739089767e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.843047657881016e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.3270729404268877e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.861700920675503e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.242043770754435e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.150554009489497e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.5120548125842106e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.442056240032798e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.232809220321542e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.091772058487322e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.278191015482662e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.4722631880867993e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.9086530395925365e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.6135780711579173e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.3382745578383037e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.4076115323623526e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.5026182964561485e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.8142834790069173e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.5164356638215395e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.0992443622015458e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.9089578624261776e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.2225956247391423e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.961740149970865e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.1574345037956846e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.700290207575563e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.408191583455846e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.78694975167582e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.4625370248211311e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.9452644767502534e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.97040017424888e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.795343962385232e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.2061311949196352e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.361828918168612e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.966578722090162e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.135044306963209e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.6585206097374794e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.289714500809282e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.699318546461882e-10 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.0503117486848623e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.984370332612343e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.508025076508602e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.707226881033421e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.06829039742729e-10 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.36753512139876e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.810143394706756e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.378114285141237e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.178907589557639e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.925201117586766e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.1817461675889263e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.511267886504356e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.3655477637541935e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.669141043389118e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.370722254762541e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.9311219290329973e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.3694687101283307e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.883123487317789e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.4665021197401984e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.7730388652003057e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.936718246360215e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.622369141950912e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.799521999947046e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.42888133231645e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.965387393445319e-11 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.888718401791948e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.604997520616052e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.306146923951701e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.885774025822684e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.991486668437517e-10 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.4298164308665946e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.2116307956944183e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.537445322393978e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.2471962068948415e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.620933952674932e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.8053345485213868e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.47334258524279e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.940802516590793e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.92162149817932e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.06450373147527e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.4762373545806895e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.1529707794343267e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.0584182115519525e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.124320523464121e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.388595715136944e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.054624522912945e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.989320080359903e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 6.672480168390393e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.300798129795112e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.227673938179578e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.867276221480864e-10 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.637609573090231e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.239459698382689e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.745507459740338e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.950937082526252e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.194930346481442e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.417934000386595e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.187774452357189e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.7705634170492885e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.516653883181789e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.958538113442046e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.334749022419146e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.326281117210783e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.0893779978669045e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 5.332101871147188e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.701417643029117e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.5007374898345915e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.76568134849731e-10 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:85: UserWarning: the float32 number -3.4028234663852886e+38 will be truncated to -10000.0
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.2451500092965944e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -4.8921705797511095e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.9146648710943737e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -5.4406001481766e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.796944839239984e-10 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.796756071177242e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.0932601429990427e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -6.479576342144355e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.3277214822314818e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -8.901123038640435e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -7.149238712145234e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.4479408722299922e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.106537249664143e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.5131773995212825e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.794818954043876e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.013643082449562e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.6220386811482967e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 3.4785532676551156e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.1350247791929178e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -9.025550085084433e-09 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 1.5151563559356873e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.3538436149929112e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.869990289866564e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.971792139623176e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 4.781808016218747e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.3767140195095635e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 7.751441444270313e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.5763561123094405e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 8.694452269253361e-09 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -3.7159978205636435e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.4768779976748192e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 2.579757918397263e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -1.268288762901193e-08 will be truncated to -1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:73: UserWarning: the float32 number 9.36368138582111e-08 will be truncated to 1e-07
warnings.warn(
/home/ubuntu/src/tjsmigration/transformers.js/scripts/float16.py:92: UserWarning: the float32 number -2.819713529333967e-08 will be truncated to -1e-07
warnings.warn(
- Quantizing to fp16: 0%| | 0/6 [00:22<?, ?it/s]
Processing /tmp/tmpv07qia3n/decoder_model_merged.onnx: 0%| | 0/1 [00:22<?, ?it/s]
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 377, in <module>
main()
File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 374, in main
quantize(input_folder, output_folder, quantization_args)
File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 309, in quantize
quantize_fp16(
File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/quantize.py", line 223, in quantize_fp16
check_and_save_model(model_fp16, save_path)
File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 29, in check_and_save_model
strict_check_model(model)
File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 21, in strict_check_model
raise e
File "/home/ubuntu/src/tjsmigration/transformers.js/scripts/utils.py", line 16, in strict_check_model
onnx.checker.check_model(model_or_path, full_check=True)
File "/home/ubuntu/.cache/uv/archive-v0/7hYcxZ8pwavXeKpAYRaHY/lib/python3.12/site-packages/onnx/checker.py", line 179, in check_model
C.check_model(
onnx.onnx_cpp2py_export.shape_inference.InferenceError: [ShapeInferenceError] Inference error(s): (op_type:If, node name: optimum::if): [ShapeInferenceError] Inference error(s): (op_type:Add, node name: /decoder/decoder/embed_positions/Add): [ShapeInferenceError] Inferred shape and existing shape differ in rank: (1) vs (0)
✅ Based on decoder_model_merged.onnx without slimming
↳ ✅ fp16: decoder_model_merged_fp16.onnx (replaced because it was invalid)
↳ ✅ int8: decoder_model_merged_int8.onnx (added)
↳ ✅ uint8: decoder_model_merged_uint8.onnx (added)
↳ ✅ q4: decoder_model_merged_q4.onnx (added)
↳ ✅ q4f16: decoder_model_merged_q4f16.onnx (added)
↳ ✅ bnb4: decoder_model_merged_bnb4.onnx (added)