Open mogoxx opened 4 months ago
+1
AttributeError: 'Qwen2Config' object has no attribute 'layer_norm_epsilon'
+1, waiting for
@mogoxx I think the crashing stack
File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py", line 1039, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py", line 734, in getitem
raise KeyError(key)
is from the transformers lib. Could you try to find out if the latest transformers lib support Qwen2?
@litaotju Stactrace ends in transformers, but begins in convert. So problem might be in both places. In my case transformers==4.39.1
and TensorRT-LLM version: 0.9.0.dev2024031900
gives me the same error:
File "/workspace/TensorRT-LLM/examples/qwen/convert_checkpoint.py", line 1421, in <module>
main()
File "/workspace/TensorRT-LLM/examples/qwen/convert_checkpoint.py", line 1216, in main
args.rms_norm_eps = hf_config.layer_norm_epsilon
File "/usr/local/lib/python3.10/dist-packages/transformers/configuration_utils.py", line 263, in __getattribute__
return super().__getattribute__(key)
AttributeError: 'Qwen2Config' object has no attribute 'layer_norm_epsilon'
+1
https://github.com/Tlntin/Qwen-TensorRT-LLM It seems implement qwen2。
For TRTLLM-0.9.0, you can refer to https://github.com/Franc-Z/QWen1.5_TensorRT-LLM
@Franc-Z your repo is not public accessible
@bao21987 repo was public yesterday...
@bao21987 Confirm, and you can access.
@bao21987 Confirm, and you can access.
can you give me the access to visit it? thanks
For TRTLLM-0.9.0, you can refer to https://github.com/Franc-Z/QWen1.5_TensorRT-LLM
I also need the access
It's reopen now @pfk-beta @ArlanCooper @deutschthomas
@litaotju Stactrace ends in transformers, but begins in convert. So problem might be in both places. In my case
transformers==4.39.1
andTensorRT-LLM version: 0.9.0.dev2024031900
gives me the same error:File "/workspace/TensorRT-LLM/examples/qwen/convert_checkpoint.py", line 1421, in <module> main() File "/workspace/TensorRT-LLM/examples/qwen/convert_checkpoint.py", line 1216, in main args.rms_norm_eps = hf_config.layer_norm_epsilon File "/usr/local/lib/python3.10/dist-packages/transformers/configuration_utils.py", line 263, in __getattribute__ return super().__getattribute__(key) AttributeError: 'Qwen2Config' object has no attribute 'layer_norm_epsilon'
+1
https://github.com/Tlntin/Qwen-TensorRT-LLM It seems implement qwen2。
from the document, it seems actually qwen1.5 ref, https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/qwen/README.md
python build.py --hf_model_dir /app/model/Qwen1.5-14B-Chat \ --dtype float16 \ --remove_input_padding \ --use_gemm_plugin float16 \ --use_gpt_attention_plugin float16 \ --use_inflight_batching \ --max_batch_size 2 \ --max_input_len 2048 \ --max_output_len 2048 \ --output_dir /app/model/trt_engines/fp16/1-gpu
Traceback (most recent call last): File "/app/tensorrt_llm/examples/qwen/build.py", line 609, in
args = parse_arguments()
File "/app/tensorrt_llm/examples/qwen/build.py", line 356, in parse_arguments
hf_config = AutoConfig.from_pretrained(
File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py", line 1039, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/usr/local/lib/python3.10/dist-packages/transformers/models/auto/configuration_auto.py", line 734, in getitem
raise KeyError(key)
KeyError: 'qwen2'