Issues
- 0
please provide a TTS prompt example for chat.
#27 opened by sipie800 - 1
How to train the speech tokneizer?
#26 opened by lucasjinreal - 4
hi,when will the train code be released? && do you train image and text tokens all in autoregressive?
#8 opened by Jiushanhuadao - 0
About input formats for training and inference
#25 opened by wen020 - 0
- 0
- 1
请教下music vocabulary size of 8192的实现
#22 opened by hhfssg - 1
关于论文中音乐tokenize和音乐生成示例的问题
#21 opened by Ash-one - 2
Loss Masking
#20 opened by gmltmd789 - 2
- 2
text chat is not so good.
#17 opened by mixiazhiyang - 1
Some weights of BertLMHeadModel were not initialized from the model checkpoint at bert-base-uncased and are newly initialized
#19 opened by rrscholarship - 2
- 1
- 1
- 1
- 1
huggingface_hub.utils._validators.HFValidationError: Repo id must be in the form 'repo_name' or 'namespace/repo_name': '/mnt/petrelfs/zhanjun.p/mllm/models/bert-base-uncased'. Use `repo_type` argument if needed.
#10 opened by Sunwood-ai-labs - 3
how many a100 it cost in training and if i want to train on v100 what is the number needed ?
#4 opened by Yang-bug-star - 3
Question about training stage and dataset
#13 opened by hyx100e - 0
Collaboration request
#6 opened by DeepDream2045 - 1
- 1
Is there any evaluation on VQA datasets?
#1 opened by jzhang38 - 1
code/dataset/model
#3 opened by darkacorn