Hi, I am facing an error when trying to convert_checkpoint qwen1.5
**model: **
https://huggingface.co/Qwen/Qwen1.5-0.5B-Chat
error:
python convert_checkpoint.py --qwen_type qwen2 --model_dir /workspace/triton/models/qwen/Qwen1.5-0.5B-Chat/ --output_dir /workspace/triton/models/qwen/trt_ckpt_Qwen1.5-0.5B-Chat_fp16_1gpu
[TensorRT-LLM] TensorRT-LLM version: 0.11.0.dev2024052100
0.11.0.dev2024052100
Traceback (most recent call last):
File "/workspace/triton/tensorrtllm_backend/tensorrt_llm/examples/qwen/convert_checkpoint.py", line 369, in
main()
File "/workspace/triton/tensorrtllm_backend/tensorrt_llm/examples/qwen/convert_checkpoint.py", line 361, in main
convert_and_save_hf(args)
File "/workspace/triton/tensorrtllm_backend/tensorrt_llm/examples/qwen/convert_checkpoint.py", line 323, in convert_and_save_hf
execute(args.workers, [convert_and_save_rank] * world_size, args)
File "/workspace/triton/tensorrtllm_backend/tensorrt_llm/examples/qwen/convert_checkpoint.py", line 329, in execute
f(args, rank)
File "/workspace/triton/tensorrtllm_backend/tensorrt_llm/examples/qwen/convert_checkpoint.py", line 309, in convert_and_save_rank
qwen = from_hugging_face(
File "/usr/local/lib/python3.10/dist-packages/tensorrt_llm/models/qwen/convert.py", line 1087, in from_hugging_face
weights = load_weights_from_hf(config=config,
File "/usr/local/lib/python3.10/dist-packages/tensorrt_llm/models/qwen/convert.py", line 1193, in load_weights_from_hf
weights = convert_hf_qwen(
File "/usr/local/lib/python3.10/dist-packages/tensorrt_llm/models/qwen/convert.py", line 931, in convert_hf_qwen
lm_head_weights = get_weight(model_params, 'lm_head', dtype)
File "/usr/local/lib/python3.10/dist-packages/tensorrt_llm/models/qwen/convert.py", line 455, in get_weight
if config[prefix + '.weight'].dtype != dtype:
KeyError: 'lm_head.weight'
NVIDIA
