Bug in recipes/quickstart/inference/local_inference/multi_modal_infer.py Results in "end_header_id|>" Preceding Generated Text

[eii-lyl]

System Info

PyTorch version: 2.5.1+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35

Python version: 3.10.16 (main, Dec 11 2024, 16:24:50) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-6.8.0-49-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3

Nvidia driver version: 550.127.05
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Address sizes: 52 bits physical, 57 bits virtual
Byte Order: Little Endian
CPU(s): 52
On-line CPU(s) list: 0-51
Vendor ID: GenuineIntel
Model name: Intel(R) Xeon(R) Platinum 8480+
CPU family: 6
Model: 143
Thread(s) per core: 2
Core(s) per socket: 26
Socket(s): 1
Stepping: 8
BogoMIPS: 4000.00
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ss ht syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon rep_good nopl xtopology cpuid tsc_known_freq pni pclmulqdq vmx ssse3 fma cx16 pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand hypervisor lahf_lm abm 3dnowprefetch cpuid_fault ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx_vnni avx512_bf16 wbnoinvd arat vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b fsrm md_clear serialize tsxldtrk avx512_fp16 arch_capabilities
Virtualization: VT-x
Hypervisor vendor: KVM
Virtualization type: full
L1d cache: 1.6 MiB (52 instances)
L1i cache: 1.6 MiB (52 instances)
L2 cache: 104 MiB (26 instances)
L3 cache: 16 MiB (1 instance)
NUMA node(s): 1
NUMA node0 CPU(s): 0-51
Vulnerability Gather data sampling: Not affected
Vulnerability Itlb multihit: Not affected
Vulnerability L1tf: Not affected
Vulnerability Mds: Not affected
Vulnerability Meltdown: Not affected
Vulnerability Mmio stale data: Unknown: No mitigations
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Not affected
Vulnerability Spec rstack overflow: Not affected
Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; TSX disabled

Versions of relevant libraries:
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.26.4
[pip3] onnx==1.17.0
[pip3] onnxruntime==1.20.1
[pip3] torch==2.5.1
[pip3] torchvision==0.20.1
[pip3] triton==3.1.0
[conda] numpy 1.26.4 pypi_0 pypi
[conda] torch 2.5.1 pypi_0 pypi
[conda] torchvision 0.20.1 pypi_0 pypi
[conda] triton 3.1.0 pypi_0 pypi

Information

• The official example scripts
• My own modified scripts

🐛 Describe the bug

When using recipes/quickstart/inference/local_inference/multi_modal_infer.py, the generated text always includes "end_header_id|>" at the beginning.

Root Cause:

The issue arises because the "add_special_tokens": True parameter in transformers/tokenization_utils_fast.py (line 526) causes the bos_token to be added at the start of the prompt. This behavior is reflected in the chat template, leading to the undesired prefix in the output.

Solution:

To resolve this, modify line 77 in recipes/quickstart/inference/local_inference/multi_modal_infer.py as follows:

inputs = processor(image, prompt, return_tensors="pt", text_kwargs={"add_special_tokens": False}).to(device)

Error logs

As described above

Expected behavior

As described above