issues
search
OpenMOSS
/
AnyGPT
Code for "AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling"
779
stars
61
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Where is output_models/mm_pretrain2/checkpoint-4000?
#46
Psychomachia
opened
5 days ago
0
Question about stage1_pretrain
#45
Psychomachia
closed
5 days ago
0
High resolution images are not found
#44
binisalegend
opened
2 weeks ago
0
Does AnyGPT support multi images input?
#43
QAQdev
closed
1 month ago
0
Details on TTS evaluation?
#42
Btlmd
opened
2 months ago
2
preprocessing audio to SpeechTokenizer codecs
#41
ehosseiniasl
opened
2 months ago
0
Regarding ASR testing
#40
Simplesss
opened
2 months ago
1
targets were set to all -100 in stage2_sft stage due to cur_len != expected_len
#39
hchc007
opened
2 months ago
0
Music Tokenizer Format
#38
ayaan-together
opened
3 months ago
0
请问大佬有做过单独模态的消融实验吗
#37
silvercherry
opened
3 months ago
1
fix:args parameters didn't pass to AnyGPTInference correctly
#36
SoftEgLi
opened
3 months ago
0
cannot import name 'split_torch_state_dict_into_shards' from 'huggingface_hub'
#35
cubxx
opened
3 months ago
0
data format in mmichat_*.jsonl
#34
hchc007
opened
3 months ago
1
请教一下关于speech的问题
#33
silvercherry
closed
3 months ago
1
Speech-to-Speech task prompt
#32
ehosseiniasl
opened
3 months ago
6
Train_loss = 0 and Eval_loss = NaN in stage2_sft
#31
xuxiaoang
opened
3 months ago
3
Question about training code
#30
Gaffey
opened
4 months ago
4
is there any way to reduce latency?
#29
kaen2891
closed
3 months ago
3
请教一下关于AnyGPT模型预训练的一些问题
#28
shihuai
closed
4 months ago
2
please provide a TTS prompt example for chat.
#27
sipie800
closed
3 months ago
1
How to train the speech tokneizer?
#26
lucasjinreal
closed
4 months ago
1
About input formats for training and inference
#25
wen020
opened
5 months ago
2
GPU resources for AnyGPT instruction turning
#24
miaozhongjian
closed
4 months ago
1
Consider next version to use LLM instead of UNet
#23
matbee-eth
closed
4 months ago
0
请教下music vocabulary size of 8192的实现
#22
hhfssg
closed
5 months ago
1
关于论文中音乐tokenize和音乐生成示例的问题
#21
Ash-one
closed
4 months ago
1
Loss Masking
#20
gmltmd789
closed
6 months ago
2
Some weights of BertLMHeadModel were not initialized from the model checkpoint at bert-base-uncased and are newly initialized
#19
rrscholarship
closed
7 months ago
1
hi，when will the pre-train related codes&scripts be released?
#18
XL2248
closed
3 months ago
4
text chat is not so good.
#17
mixiazhiyang
closed
7 months ago
2
can i ask the model to choose which of the voices sound more natural?
#16
s-j-chung
closed
7 months ago
2
RuntimeError: Error(s) in loading state_dict for SoundStorm
#15
empty2enrich
closed
4 months ago
1
qformer_quantizer.py missing keys: 511 unexpected keys: 146
#14
empty2enrich
closed
7 months ago
1
Question about training stage and dataset
#13
hyx100e
closed
7 months ago
3
add Docker
#12
Sunwood-ai-labs
opened
7 months ago
0
Bug Fix (#9, #10) & README JP & Update README
#11
Sunwood-ai-labs
opened
7 months ago
0
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
Sunwood-ai-labs
closed
7 months ago
1
ModuleNotFoundError: No module named 'mmgpt.src'
#9
Sunwood-ai-labs
closed
7 months ago
1
hi，when will the train code be released? && do you train image and text tokens all in autoregressive?
#8
Jiushanhuadao
closed
3 months ago
7
add JP readme
#7
Sunwood-ai-labs
closed
7 months ago
0
Collaboration request
#6
DeepDream2045
closed
7 months ago
0
When will code, dataset and checkpoints be released?
#5
QAQdev
closed
8 months ago
1
how many a100 it cost in training and if i want to train on v100 what is the number needed ?
#4
Yang-bug-star
closed
7 months ago
4
code/dataset/model
#3
darkacorn
closed
8 months ago
1
Update README.md
#2
eltociear
closed
8 months ago
1
Is there any evaluation on VQA datasets?
#1
jzhang38
closed
8 months ago
1