dataplayer12/phi-4-Q6_K
Updated
•
21
Jaiyam Sharma
dataplayer12
·
AI & ML interests
Computer Vision
Recent Activity
updated
a model
6 days ago
dataplayer12/phi-4-Q6_K
published
a model
6 days ago
dataplayer12/phi-4-Q6_K
updated
a model
7 days ago
dataplayer12/phi-4-Q4_K_M
Organizations
None yet
dataplayer12's activity
updated
a
model
6 days ago
published
a
model
6 days ago
updated
a
model
7 days ago
published
a
model
7 days ago
liked
a
model
7 days ago
reacted to
chansung's
post with 👍
7 days ago
Post
1981
Simple summary on DeepSeek AI's Janus-Pro: A fresh take on multimodal AI!
It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.
Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
✦ Stage 3: Fine-tuning with a careful balance of multimodal data.
Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.
The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.
It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.
Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
✦ Stage 3: Fine-tuning with a careful balance of multimodal data.
Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.
The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.
updated
a
model
8 days ago
published
a
model
8 days ago
liked
2
models
about 1 year ago
Does not work with NeMo container
3
#2 opened almost 2 years ago
by
dataplayer12
gibberish on 4090
1
#4 opened almost 2 years ago
by
lizelive
liked
a
dataset
over 2 years ago