vllm
vllm copied to clipboard
Published
1 week ago
•
vllm-project
vllm-project
[Bug]: Unable to load the tokenizers of certain models
Your current environment
The output of `python collect_env.py`
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A
OS: Red Hat Enterprise Linux 9.4 (Plow) (x86_64)
GCC version: (GCC) 11.4.1 20231218 (Red Hat 11.4.1-3)
Clang version: Could not collect
CMake version: version 3.29.5
Libc version: glibc-2.34
Python version: 3.10.9 (main, Mar 8 2023, 10:47:38) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.14.0-427.31.1.el9_4.x86_64-x86_64-with-glibc2.34
Is CUDA available: False
CUDA runtime version: 12.1.105
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: Could not collect
Nvidia driver version: Could not collect
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: 48 bits physical, 48 bits virtual
Byte Order: Little Endian
CPU(s): 128
On-line CPU(s) list: 0-127
Vendor ID: AuthenticAMD
Model name: AMD EPYC 7H12 64-Core Processor
CPU family: 23
Model: 49
Thread(s) per core: 1
Core(s) per socket: 64
Socket(s): 2
Stepping: 0
Frequency boost: disabled
CPU(s) scaling MHz: 100%
CPU max MHz: 2600.0000
CPU min MHz: 1500.0000
BogoMIPS: 5190.57
Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif v_spec_ctrl umip rdpid overflow_recov succor smca
Virtualization: AMD-V
L1d cache: 4 MiB (128 instances)
L1i cache: 4 MiB (128 instances)
L2 cache: 64 MiB (128 instances)
L3 cache: 512 MiB (32 instances)
NUMA node(s): 8
NUMA node0 CPU(s): 0-15
NUMA node1 CPU(s): 16-31
NUMA node2 CPU(s): 32-47
NUMA node3 CPU(s): 48-63
NUMA node4 CPU(s): 64-79
NUMA node5 CPU(s): 80-95
NUMA node6 CPU(s): 96-111
NUMA node7 CPU(s): 112-127
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: Not affected
Vulnerability Retbleed: Mitigation; untrained return thunk; SMT disabled
Vulnerability Spec rstack overflow: Mitigation; SMT disabled
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; Retpolines, IBPB conditional, STIBP disabled, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Not affected
Versions of relevant libraries:
[pip3] numpy==1.26.4
[pip3] nvidia-cublas-cu12==12.1.3.1
[pip3] nvidia-cuda-cupti-cu12==12.1.105
[pip3] nvidia-cuda-nvrtc-cu12==12.1.105
[pip3] nvidia-cuda-runtime-cu12==12.1.105
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.0.2.54
[pip3] nvidia-curand-cu12==10.3.2.106
[pip3] nvidia-cusolver-cu12==11.4.5.107
[pip3] nvidia-cusparse-cu12==12.1.0.106
[pip3] nvidia-ml-py==12.555.43
[pip3] nvidia-nccl-cu12==2.20.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.1.105
[pip3] pyzmq==26.0.2
[pip3] torch==2.4.0
[pip3] torchvision==0.19.0
[pip3] transformers==4.45.1
[pip3] triton==3.0.0
[conda] numpy 1.26.4 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.1.3.1 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.1.105 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.1.105 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.1.105 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.1.0.70 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.0.2.54 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.2.106 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.4.5.107 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.1.0.106 pypi_0 pypi
[conda] nvidia-ml-py 12.555.43 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.20.5 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.1.105 pypi_0 pypi
[conda] pyzmq 26.0.2 pypi_0 pypi
[conda] torch 2.4.0 pypi_0 pypi
[conda] torchvision 0.19.0 pypi_0 pypi
[conda] transformers 4.45.1 pypi_0 pypi
[conda] triton 3.0.0 pypi_0 pypi
ROCM Version: Could not collect
Neuron SDK Version: N/A
vLLM Version: 0.6.3.dev50+gbe76e5aa.d20240930
vLLM Build Flags:
CUDA Archs: Not Set; ROCm: Disabled; Neuron: Disabled
GPU Topology:
Could not collect
Model Input Dumps
No response
🐛 Describe the bug
I am trying to load llama-2-13B and alma-13B models and I am gettign errors related to the tokenizers. note that loading the 7B version of the models works fine. vllm and transformers versions that I am using are shown in the environment details.
Here is the log of the errors:
llama-2-13B
model = LLM(model=name_path,seed=42,trust_remote_code=True,tensor_parallel_size=1)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 214, in __init__
self.llm_engine = LLMEngine.from_engine_args(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 574, in from_engine_args
engine = cls(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 309, in __init__
self.tokenizer = self._init_tokenizer()
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 618, in _init_tokenizer
return init_tokenizer_from_configs(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/__init__.py", line 28, in init_tokenizer_from_configs
return get_tokenizer_group(parallel_config.tokenizer_pool_config,
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/__init__.py", line 49, in get_tokenizer_group
return tokenizer_cls.from_config(tokenizer_pool_config, **init_kwargs)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/tokenizer_group.py", line 30, in from_config
return cls(**init_kwargs)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/tokenizer_group.py", line 23, in __init__
self.tokenizer = get_tokenizer(self.tokenizer_id, **tokenizer_config)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer.py", line 140, in get_tokenizer
raise e
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer.py", line 119, in get_tokenizer
tokenizer = AutoTokenizer.from_pretrained(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 907, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2216, in from_pretrained
return cls._from_pretrained(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2431, in _from_pretrained
tokenizer_file_handle = json.load(tokenizer_file_handle)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/json/__init__.py", line 293, in load
return loads(fp.read(),
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/json/__init__.py", line 346, in loads
return _default_decoder.decode(s)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/json/decoder.py", line 340, in decode
raise JSONDecodeError("Extra data", s, end)
json.decoder.JSONDecodeError: Extra data: line 93391 column 2 (char 1700995)
Traceback (most recent call last):
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/convert_slow_tokenizer.py", line 1592, in convert_slow_tokenizer
).converted()
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/convert_slow_tokenizer.py", line 1489, in converted
tokenizer = self.tokenizer()
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/convert_slow_tokenizer.py", line 1482, in tokenizer
vocab_scores, merges = self.extract_vocab_merges_from_model(self.vocab_file)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/convert_slow_tokenizer.py", line 1458, in extract_vocab_merges_from_model
bpe_ranks = load_tiktoken_bpe(tiktoken_url)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/tiktoken/load.py", line 148, in load_tiktoken_bpe
return {
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/tiktoken/load.py", line 150, in <dictcomp>
for token, rank in (line.split() for line in contents.splitlines() if line)
ValueError: not enough values to unpack (expected 2, got 1)
During handling of the above exception, another exception occurred:
alma-13B
model = LLM(model=name_path,seed=42,trust_remote_code=True,tensor_parallel_size=1)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/entrypoints/llm.py", line 214, in __init__
self.llm_engine = LLMEngine.from_engine_args(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 574, in from_engine_args
engine = cls(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 309, in __init__
self.tokenizer = self._init_tokenizer()
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/engine/llm_engine.py", line 618, in _init_tokenizer
return init_tokenizer_from_configs(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/__init__.py", line 28, in init_tokenizer_from_configs
return get_tokenizer_group(parallel_config.tokenizer_pool_config,
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/__init__.py", line 49, in get_tokenizer_group
return tokenizer_cls.from_config(tokenizer_pool_config, **init_kwargs)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/tokenizer_group.py", line 30, in from_config
return cls(**init_kwargs)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer_group/tokenizer_group.py", line 23, in __init__
self.tokenizer = get_tokenizer(self.tokenizer_id, **tokenizer_config)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer.py", line 140, in get_tokenizer
raise e
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/vllm/transformers_utils/tokenizer.py", line 119, in get_tokenizer
tokenizer = AutoTokenizer.from_pretrained(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/models/auto/tokenization_auto.py", line 907, in from_pretrained
return tokenizer_class.from_pretrained(pretrained_model_name_or_path, *inputs, **kwargs)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2216, in from_pretrained
return cls._from_pretrained(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/tokenization_utils_base.py", line 2450, in _from_pretrained
tokenizer = cls(*init_inputs, **init_kwargs)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/models/llama/tokenization_llama_fast.py", line 157, in __init__
super().__init__(
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/tokenization_utils_fast.py", line 138, in __init__
fast_tokenizer = convert_slow_tokenizer(self, from_tiktoken=True)
File "/home/wmohammed/.conda/envs/alti/lib/python3.10/site-packages/transformers/convert_slow_tokenizer.py", line 1594, in convert_slow_tokenizer
raise ValueError(
ValueError: Converting from Tiktoken failed, if a converter for SentencePiece is available, provide a model path with a SentencePiece tokenizer.model file.Currently available slow->fast convertors: ['AlbertTokenizer', 'BartTokenizer', 'BarthezTokenizer', 'BertTokenizer', 'BigBirdTokenizer', 'BlenderbotTokenizer', 'CamembertTokenizer', 'CLIPTokenizer', 'CodeGenTokenizer', 'ConvBertTokenizer', 'DebertaTokenizer', 'DebertaV2Tokenizer', 'DistilBertTokenizer', 'DPRReaderTokenizer', 'DPRQuestionEncoderTokenizer', 'DPRContextEncoderTokenizer', 'ElectraTokenizer', 'FNetTokenizer', 'FunnelTokenizer', 'GPT2Tokenizer', 'HerbertTokenizer', 'LayoutLMTokenizer', 'LayoutLMv2Tokenizer', 'LayoutLMv3Tokenizer', 'LayoutXLMTokenizer', 'LongformerTokenizer', 'LEDTokenizer', 'LxmertTokenizer', 'MarkupLMTokenizer', 'MBartTokenizer', 'MBart50Tokenizer', 'MPNetTokenizer', 'MobileBertTokenizer', 'MvpTokenizer', 'NllbTokenizer', 'OpenAIGPTTokenizer', 'PegasusTokenizer', 'Qwen2Tokenizer', 'RealmTokenizer', 'ReformerTokenizer', 'RemBertTokenizer', 'RetriBertTokenizer', 'RobertaTokenizer', 'RoFormerTokenizer', 'SeamlessM4TTokenizer', 'SqueezeBertTokenizer', 'T5Tokenizer', 'UdopTokenizer', 'WhisperTokenizer', 'XLMRobertaTokenizer', 'XLNetTokenizer', 'SplinterTokenizer', 'XGLMTokenizer', 'LlamaTokenizer', 'CodeLlamaTokenizer', 'GemmaTokenizer', 'Phi3Tokenizer']
Before submitting a new issue...
- [X] Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.
sure, it is:
name_path=meta-llama/Llama-2-13b-hf
name_path=haoranxu/ALMA-13B
Is a transformers bug: https://github.com/huggingface/transformers/issues/33746
Are you sure you have tokenizers installed?
from transformers import AutoTokenizer
AutoTokenizer.from_pretrained('haoranxu/ALMA-13B')
has not issues for me unless I uninstall sentencepiece: https://huggingface.co/haoranxu/ALMA-13B/tree/main does not have a tokenizers.json. you need it for the conversion.
The error is missleading however
I do have sentencepiece and tokenizers installed. Can you please share the versions of:
- vllm
- transformers
- tokenizers
- sentencepiece that are working for you?
I have created a new env with those exact versions and I am still not able to load the models. I am able to locate the error to be coming from this file https://github.com/huggingface/transformers/blob/main/src/transformers/convert_slow_tokenizer.py In specific, the ValueError in line 1597 is being raised
Let's focus this on https://github.com/huggingface/transformers/issues/33746 I think this is an environnement issue!
I was with a similar issue in Databricks environment and solved it with: dbutils.library.restartPython()
This issue has been automatically marked as stale because it has not had any activity within 90 days. It will be automatically closed if no further activity occurs within 30 days. Leave a comment if you feel this issue should remain open. Thank you!
![github-actions[bot] avatar](https://avatars.githubusercontent.com/in/15368?v=4 "Published by a pub.dev verified publisher"){kind=small}
This issue has been automatically closed due to inactivity. Please feel free to reopen if you feel it is still relevant. Thank you!