ylying

 I used cameras.py to convert coordinations. I convert a 2dpoint to camera coordination in camera 0 and 1, and the result camera coordinations are right as annotation describe.But when...

how to align Mandarin dataset by mfa？

5

the Mandarin lexicon.txt in your project seems different from mfa pretrained model and it will failed to align，saying "There were phones in the dictionary that do not have acoustic models"...

“No backend type associated with device type cpu” when run cli_demo_sat.py

5

``` Traceback (most recent call last): File "/ssd/ylying/CogVLM/basic_demo/infer_dataset.py", line 164, in main() File "/ssd/ylying/CogVLM/basic_demo/infer_dataset.py", line 36, in main model, model_args = AutoModel.from_pretrained( File "/usr/local/lib/python3.10/dist-packages/sat/model/base_model.py", line 367, in from_pretrained mp_split_model_receive(model, use_node_group=use_node_group)...

What is the difference between id_to_token() and decode() in tokenizer?

1

 If I use tokenizer.id_to_token(), the text is very strange, but if I use tokenizer.decode() to decode ids, the result is right. Are these two method different?

Accuracy reduction of Lora

1

I used lora trained on qwen2（using the lora code just updated recent weeks）, but the accuracy of test dataset reduced from 75 to 67. Then I merged lora weights into...

model-name和chat template绑定的吗？

2

这是我的命令 lmdeploy serve api_server /mnt/data/OmChat-40B-IV --backend pytorch --server-port 8000 --model-name my_model_abc 报错 `ValueError: You are using base template to handle chat task. Please specify a `--chat-template` name chosen from `lmdeploy...