We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
I followed this procedure, but I encountered a problem that I don't think is on my side.
https://github.com/NSFW-API/TripleX/blob/master/guides/fine_tuning_hunyuan_video_with_finetrainers.md
First, I had to solve what appears to be a requirement for a different configuration format, because the script reported this error when executed:
train.py: error: the following arguments are required: --dataset_config
But the unsolvable problem was when the script tries to download the file https://huggingface.co/tencent/HunyuanVideo/resolve/main/model_index.json- and it's not there. I searched but simply couldn't find it anywhere. And I also can't manage to create it.
(venv) [[email protected] ](mailto:[email protected]):/workspace/finetrainers$ ./train_hunyuan_video.sh Running command: accelerate launch --config_file accelerate_configs/compiled_1.yaml --gpu_ids 0 train.py --model_name hunyuan_video --pretrained_model_name_or_path tencent/HunyuanVideo --dataset_config dataset_config.json --dataloader_num_workers 0 --training_type lora --seed 42 --mixed_precision bf16 --batch_size 1 --train_steps 500 --rank 128 --lora_alpha 128 --gradient_checkpointing --gradient_accumulation_steps 1 --checkpointing_steps 500 --checkpointing_limit 2 --enable_slicing --enable_tiling --precompute_conditions --optimizer adamw --lr 2e-5 --lr_scheduler constant_with_warmup --lr_warmup_steps 100 --beta1 0.9 --beta2 0.95 --weight_decay 2e-5 --epsilon 1e-8 --max_grad_norm 1.0 --tracker_name finetrainers-hunyuan-video --output_dir /workspace/finetrainers/data/trained --nccl_timeout 1800 --report_to wandb 2025-03-23 20:57:12,625 - finetrainers - ERROR - An error occurred during training: 404 Client Error. (Request ID: Root=1-67e075a8-614d83426533b4655439fb87;a92cd778-cc3b-42b4-ad11-7c70fa795fb5) Entry Not Found for url: [https://huggingface.co/tencent/HunyuanVideo/resolve/main/model_index.json ](https://huggingface.co/tencent/HunyuanVideo/resolve/main/model_index.json). 2025-03-23 20:57:12,627 - finetrainers - ERROR - Traceback (most recent call last): File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 409, in hf_raise_for_status response.raise_for_status() File "/workspace/finetrainers/venv/lib/python3.10/site-packages/requests/models.py", line 1024, in raise_for_status raise HTTPError(http_error_msg, response=self) requests.exceptions.HTTPError: 404 Client Error: Not Found for url: https://huggingface.co/tencent/HunyuanVideo/resolve/main/model_index.json The above exception was the direct cause of the following exception: Traceback (most recent call last): File "/workspace/finetrainers/train.py", line 46, in main model_specification = model_specification_cls( File "/workspace/finetrainers/finetrainers/models/hunyuan_video/base_specification.py", line 91, in init super().init( File "/workspace/finetrainers/finetrainers/models/modeling_utils.py", line 73, in init self._load_configs() File "/workspace/finetrainers/finetrainers/models/modeling_utils.py", line 237, in _load_configs self._load_transformer_config() File "/workspace/finetrainers/finetrainers/models/modeling_utils.py", line 253, in _load_transformer_config transformer_cls = resolve_component_cls( File "/workspace/finetrainers/finetrainers/utils/model.py", line 20, in resolve_component_cls index_path = hf_hub_download( File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 862, in hf_hub_download return _hf_hub_download_to_cache_dir( File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 925, in _hf_hub_download_to_cache_dir (url_to_download, etag, commit_hash, expected_size, head_call_error) = _get_metadata_or_catch_error( File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1376, in _get_metadata_or_catch_error metadata = get_hf_file_metadata( File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/utils/_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 1296, in get_hf_file_metadata r = _request_wrapper( File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 280, in _request_wrapper response = _request_wrapper( File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/file_download.py", line 304, in _request_wrapper hf_raise_for_status(response) File "/workspace/finetrainers/venv/lib/python3.10/site-packages/huggingface_hub/utils/_http.py", line 420, in hf_raise_for_status raise _format(EntryNotFoundError, message, response) from e huggingface_hub.errors.EntryNotFoundError: 404 Client Error. (Request ID: Root=1-67e075a8-614d83426533b4655439fb87;a92cd778-cc3b-42b4-ad11-7c70fa795fb5) Entry Not Found for url: [https://huggingface.co/tencent/HunyuanVideo/resolve/main/model_index.json ](https://huggingface.co/tencent/HunyuanVideo/resolve/main/model_index.json). Has anyone encountered this issue? Thank you!
The text was updated successfully, but these errors were encountered:
No branches or pull requests
I followed this procedure, but I encountered a problem that I don't think is on my side.
https://github.com/NSFW-API/TripleX/blob/master/guides/fine_tuning_hunyuan_video_with_finetrainers.md
First, I had to solve what appears to be a requirement for a different configuration format, because the script reported this error when executed:
train.py: error: the following arguments are required: --dataset_config
But the unsolvable problem was when the script tries to download the file https://huggingface.co/tencent/HunyuanVideo/resolve/main/model_index.json- and it's not there.
I searched but simply couldn't find it anywhere. And I also can't manage to create it.
The text was updated successfully, but these errors were encountered: