Using π€ to Train a GPT-2 Model for Music Generation
β’
8
Juan Carlos PiΓ±eros
juancopi81
AI & ML interests
Music and AI
Recent Activity
liked
a Space
3 days ago
tencent/Hunyuan3D-2
liked
a Space
8 days ago
hexgrad/Kokoro-TTS
Articles
Organizations
juancopi81's activity
reacted to
aiqcamp's
post with π₯
3 days ago
Post
3217
# π¨ FLUX Diagram Generator - Create Hand-Drawn Style Diagrams
aiqcamp/diagram
Generate beautiful mind maps and diagrams with AI! Using the FLUX.1-schnell model, create natural hand-drawn style diagrams that bring your ideas to life.
## β¨ Key Features
- π‘ Intuitive prompt-based input system
- π― Rich examples including knowledge trees, digital transformation, creative process, and more
- π Customizable settings for image size, seed values, and more
- πΌ Support for resolutions up to 2048x2048
- β‘ Fast generation (4 steps default)
## π― Use Cases
- Educational materials
- Project planning
- Idea structuring
- Presentation visuals
- Business process visualization
Built with Gradio for a user-friendly interface that anyone can use. Start creating your own diagrams now! π
Try it out to transform your ideas into visually appealing diagrams with a unique hand-drawn aesthetic.
#AIart #Diagram #Mindmap #Visualization #HuggingFace
aiqcamp/diagram
Generate beautiful mind maps and diagrams with AI! Using the FLUX.1-schnell model, create natural hand-drawn style diagrams that bring your ideas to life.
## β¨ Key Features
- π‘ Intuitive prompt-based input system
- π― Rich examples including knowledge trees, digital transformation, creative process, and more
- π Customizable settings for image size, seed values, and more
- πΌ Support for resolutions up to 2048x2048
- β‘ Fast generation (4 steps default)
## π― Use Cases
- Educational materials
- Project planning
- Idea structuring
- Presentation visuals
- Business process visualization
Built with Gradio for a user-friendly interface that anyone can use. Start creating your own diagrams now! π
Try it out to transform your ideas into visually appealing diagrams with a unique hand-drawn aesthetic.
#AIart #Diagram #Mindmap #Visualization #HuggingFace
- 1 reply
liked
a
Space
3 days ago
liked
a
Space
8 days ago
Adding `safetensors` variant of this model
#1 opened 9 days ago
by
SFconvertbot
Wish it woukd be more longer than ~17s
5
#15 opened 12 months ago
by
FashionStash
liked
2
Spaces
about 1 month ago
What stands out to you the most?
5
#4 opened about 2 months ago
by
fdaudens
liked
3
Spaces
about 2 months ago
Update requirements.txt
#18 opened 2 months ago
by
Beesa
liked
a
Space
3 months ago
liked
a
Space
4 months ago
upvoted
an
article
4 months ago
Article
Recoloring photos with diffusers
By
β’
β’
28
updated
a
dataset
4 months ago
reacted to
FeYuan's
post with π₯
7 months ago
Post
4770
Hi everyone,
I am excited to introduce our latest work, LLaMAX. πππ
LLaMAX is a powerful language model created specifically for multilingual scenarios. Built upon Meta's LLaMA series models, LLaMAX undergoes extensive training across more than 100 languages.
Remarkably, it enhances its multilingual capabilities without compromising its generalization ability, surpassing existing LLMs.
β¨Highlights:
π LLaMAX supports the 102 languages covered by Flores-101, and its performance in translating between low-resource languages far surpasses other decoder-only LLMs.
π Even for languages not covered in Flores-200, LLaMAX still shows significant improvements in translation performance.
π By performing simple SFT on English task data, LLaMAX demonstrates impressive multilingual transfer abilities in downstream tasks.
π In our paper, we discuss effective methods for enhancing the multilingual capabilities of LLMs during the continued training phase.
We welcome you to use our model and provide feedback.
More Details:
π Code: https://github.com/CONE-MT/LLaMAX/
π Model: https://huggingface.co./LLaMAX/
I am excited to introduce our latest work, LLaMAX. πππ
LLaMAX is a powerful language model created specifically for multilingual scenarios. Built upon Meta's LLaMA series models, LLaMAX undergoes extensive training across more than 100 languages.
Remarkably, it enhances its multilingual capabilities without compromising its generalization ability, surpassing existing LLMs.
β¨Highlights:
π LLaMAX supports the 102 languages covered by Flores-101, and its performance in translating between low-resource languages far surpasses other decoder-only LLMs.
π Even for languages not covered in Flores-200, LLaMAX still shows significant improvements in translation performance.
π By performing simple SFT on English task data, LLaMAX demonstrates impressive multilingual transfer abilities in downstream tasks.
π In our paper, we discuss effective methods for enhancing the multilingual capabilities of LLMs during the continued training phase.
We welcome you to use our model and provide feedback.
More Details:
π Code: https://github.com/CONE-MT/LLaMAX/
π Model: https://huggingface.co./LLaMAX/
- 3 replies
updated
a
model
7 months ago
Set `library_name` to `tf-keras`.
1
#1 opened 7 months ago
by
Wauplin
reacted to
gokaygokay's
post with π
7 months ago
Post
4059
I've created a space for chatting with Gemma 2 using llama.cpp
- ποΈ Choose between 27B IT and 9b IT models
- π Fast inference using llama.cpp
- gokaygokay/Gemma-2-llamacpp
- ποΈ Choose between 27B IT and 9b IT models
- π Fast inference using llama.cpp
- gokaygokay/Gemma-2-llamacpp
-
- 1 reply