Hugging Face's logo
AI Safety Research's picture
15 11 141

AI Safety Research

AISafety
21world's profile picture Viewegger's profile picture t-edward's profile picture
ยท
https://humanaligned.ai

AI & ML interests

LLMs, planning, EA

Recent Activity

liked a model 5 days ago
bcywinski/SAeUron
replied to sayakpaul's post 22 days ago
We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc. We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links: * Models and datasets: https://huggingface.co/finetrainers * finetrainers: https://github.com/a-r-r-o-w/finetrainers * LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
reacted to sayakpaul's post with ๐Ÿ”ฅ 22 days ago
We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc. We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links: * Models and datasets: https://huggingface.co/finetrainers * finetrainers: https://github.com/a-r-r-o-w/finetrainers * LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
View all activity

Organizations

Hugging Face Discord Community's profile picture

AISafety's activity

liked a model 5 days ago
replied to sayakpaul's post 22 days ago
reacted to sayakpaul's post with ๐Ÿ”ฅ 22 days ago
view post
Post
1963
We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc.

We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links:

* Models and datasets: https://huggingface.co/finetrainers
* finetrainers: https://github.com/a-r-r-o-w/finetrainers
* LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py
  • 1 reply
ยท
liked 4 models 23 days ago
liked a Space 26 days ago
liked a model 26 days ago
upvoted an article 26 days ago
view article
Article

Open-R1: a fully open reproduction of DeepSeek-R1

โ€ข 770
liked 3 models about 1 month ago
liked 2 Spaces about 1 month ago
liked a model about 1 month ago
New activity in hexgrad/Kokoro-82M about 2 months ago

Synthetic Data Collection PAUSED Jan 16

30
#21 opened about 2 months ago by
hexgrad
reacted to hexgrad's post with ๐Ÿš€ about 2 months ago
view post
Post
19861
๐Ÿ“ฃ Looking for labeled, high-quality synthetic audio/TTS data ๐Ÿ“ฃ Have you been or are you currently calling API endpoints from OpenAI, ElevenLabs, etc? Do you have labeled audio data sitting around gathering dust? Let's talk! Join https://discord.gg/QuGxSWBfQy or comment down below.

If your data exceeds quantity & quality thresholds and is approved into the next hexgrad/Kokoro-82M training mix, and you permissively DM me the data under an effective Apache license, then I will DM back the corresponding voicepacks for YOUR data if/when the next Apache-licensed Kokoro base model drops.

What does this mean? If you've been calling closed-source TTS or audio API endpoints to:
- Build voice agents
- Make long-form audio, like audiobooks or podcasts
- Handle customer support, etc
Then YOU can contribute to the training mix and get useful artifacts in return. โค๏ธ

More details at hexgrad/Kokoro-82M#21
ยท
liked 2 Spaces about 2 months ago