Bin Xiao
leoxiaobin
AI & ML interests
Large-scale Foundation Model Training; Computer Vision; Deep Learning
Organizations
leoxiaobin's activity
Fix invalid escape sequences
#65 opened 2 months ago
by
jkawamoto
Add get_output_embeddings
2
#18 opened 3 months ago
by
xray1111
Fix generation when `repetition_penalty` is activated
#57 opened 3 months ago
by
YenChunChen
Fix number of image tokens
#51 opened 3 months ago
by
mber
update_model_init_fp16
1
#53 opened 3 months ago
by
haipingwu
update_model_init_fp16
1
#20 opened 3 months ago
by
haipingwu
update_model_init_fp16
1
#12 opened 3 months ago
by
haipingwu
update_model_init_fp16
1
#20 opened 3 months ago
by
haipingwu
update_ocr_postprocess
1
#19 opened 3 months ago
by
haipingwu
update_ocr_postprocess
1
#19 opened 3 months ago
by
haipingwu
update_ocr_postprocess
1
#11 opened 3 months ago
by
haipingwu
update_ocr_postprocess
1
#52 opened 3 months ago
by
haipingwu
Rewrite image embedding to remove the in-place op
4
#53 opened 3 months ago
by
YenChunChen
Use Flash Attention for CLIP image encoder
1
#52 opened 3 months ago
by
YenChunChen
Fix modeling code (typos/bugs)
#6 opened 4 months ago
by
Xenova
Fix modeling code (typos/bugs)
#10 opened 4 months ago
by
Xenova
Fix modeling code (typos/bugs)
#5 opened 4 months ago
by
Xenova
Fix modeling code (typos/bugs)
5
#12 opened 4 months ago
by
Xenova
Fix incorrect bos_token, eos_token, and pad_token ids in config.json
#7 opened 4 months ago
by
Xenova
Fix incorrect bos_token, eos_token, and pad_token ids in config.json
#11 opened 4 months ago
by
Xenova
Fix incorrect bos_token, eos_token, and pad_token ids in config.json
#6 opened 4 months ago
by
Xenova
Fix runon lines
#16 opened 4 months ago
by
milekpl
Fix incorrect bos_token, eos_token, and pad_token ids in config.json
3
#17 opened 4 months ago
by
Xenova
add caption with grounding tasks
3
#3 opened 4 months ago
by
leoxiaobin
add_caption_grounding
#23 opened 4 months ago
by
haipingwu
Add caption+grounding tasks
#1 opened 4 months ago
by
leoxiaobin
update_readme_example
#3 opened 4 months ago
by
haipingwu
add_grounding_example
#3 opened 4 months ago
by
haipingwu
update_readme_example
#3 opened 4 months ago
by
haipingwu
update_readme_example
#5 opened 4 months ago
by
haipingwu
add_grounding_example
#3 opened 4 months ago
by
haipingwu
add_grounding_example
#2 opened 4 months ago
by
haipingwu
add_grounding_example
#2 opened 4 months ago
by
haipingwu
add_grounding_example
#2 opened 4 months ago
by
haipingwu
add_grounding_example
#2 opened 4 months ago
by
haipingwu
init_model
#1 opened 4 months ago
by
haipingwu
init_model
#1 opened 4 months ago
by
haipingwu
init_model
#1 opened 4 months ago
by
haipingwu
clean_sample_code
1
#36 opened 4 months ago
by
haipingwu
Make flash attention configurable in user code
4
#26 opened 5 months ago
by
YenChunChen
Published paper
1
#28 opened 5 months ago
by
Napron
correct the paper reference
#25 opened 5 months ago
by
g1y5x3
onnx version
1
#13 opened 5 months ago
by
guidevops
Inference via TGI
3
#4 opened 5 months ago
by
abrakaa
phi3 vision visual encoder
9
#2 opened 5 months ago
by
the-future-dev
is it possible to use vision model with V100?
2
#3 opened 5 months ago
by
textToSQL
How to give it a system prompt?
2
#1 opened 5 months ago
by
catworld1212