issues
search
Efficient-Large-Model
/
VILA
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
Apache License 2.0
877
stars
55
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Updated Mixtral for Long-context and Fake Gradient
#29
yukang2017
closed
2 months ago
0
Model checkpoints before supervised fine-tuning
#28
CRazorback
closed
1 week ago
1
Missing deepspeed config files in training scripts
#27
AoyuQC
closed
2 months ago
2
Question on Multi-Image Input Processing During Training
#26
gaozhihan
opened
2 months ago
0
Cannot correctly recognize <im_patch>
#25
m2408gj
opened
2 months ago
1
What're the modifications in `llava/train/transformers_replace`?
#24
ys-zong
opened
2 months ago
3
Intermediate stages checkpoints
#23
sarvghotra
closed
3 months ago
2
More data leading to lower indicators?
#22
uniquehou
closed
3 months ago
3
What's the purpose of func repack_multimodal_data?
#21
BlueBlueFF
closed
3 months ago
1
Multi-image Input Inference Script
#20
gaozhihan
closed
3 months ago
2
unexpected keyword argument 'seqlens_in_batch'
#19
katopz
closed
3 months ago
3
Index error when conversations is short. (/aten/src/ATen/native/cuda/IndexKernel.cu:)
#18
hzhang57
closed
3 months ago
1
Multi-image is worse than concat them as single image.
#17
liuweijie19980216
opened
3 months ago
2
AWQ Tinychat tensor mismatch RuntimeError
#16
leon-seidel
closed
2 months ago
1
License
#15
fakerybakery
closed
3 months ago
2
Base LLM for the VILA 7B Model
#14
shikhar-srivastava
closed
3 months ago
2
FlashAttention Bug
#13
rzyfrank
closed
3 months ago
5
Is stage2 neccessary?
#12
peibinchen
closed
3 months ago
6
KeyError: 'llava_llama'
#11
huzicong
closed
3 months ago
2
Inference has error: TypeError: LlamaForCausalLM.forward() got an unexpected keyword argument 'seqlens_in_batch'
#10
hzhang57
closed
3 months ago
4
'is_gemma_tokenizer' cannot be imported in llava.mm_utils
#9
peibinchen
closed
3 months ago
1
Having trouble running multi-image input inference.
#8
HiHiAllen
closed
3 months ago
3
About the VideoQA dataset
#7
Yxxxb
closed
3 months ago
2
update project.toml.
#6
Seerkfang
closed
3 months ago
0
[Feature Request] Evaluation tools of the Few-shot VQA/Caption
#5
Li-Qingyun
opened
3 months ago
6
Can't run inference demo
#4
zyddnys
closed
2 months ago
6
Add llava/eval from VILA-Internal and edit the README.md
#3
yueshen2016
closed
4 months ago
0
LoRA for downstream task tuning
#2
hzhang57
closed
4 months ago
3
upload demo videos
#1
Lyken17
closed
3 months ago
3
Previous