Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts

Join Posts waitlist
Taylor658Β 
posted an update about 3 hours ago
fdaudensΒ 
posted an update about 5 hours ago
view post
Post
247
I've added new collections to the Journalists on πŸ€— community, focusing on Data Visualization, Optical Character Recognition, and Multimodal Models:

- TinyChart-3B: This model interprets data visualizations based on your prompts. It can generate the underlying data table from a chart or recreate the chart with Python code.
- PDF to OCR: Convert your PDFs to textβ€”ideal for FOI records sent as images.
- Idefics-8b: A multimodal model that allows you to ask questions about images.

Explore these tools here: πŸ‘‰ https://huggingface.co/JournalistsonHF
LocutusqueΒ 
posted an update about 7 hours ago
view post
Post
338
Introducing llama-3-neural-chat-v2.2-8b! This powerful conversational AI model builds on Meta's Llama 3, fine-tuned by Locutusque for enhanced performance in coding, math & writing.

Locutusque/llama-3-neural-chat-v2.2-8B
naterawΒ 
posted an update about 7 hours ago
santiviquezΒ 
posted an update about 10 hours ago
view post
Post
375
Looking for someone with +10 years of experience training Deep Kolmogorov-Arnold Networks.

Any suggestions?
Undi95Β 
posted an update about 10 hours ago
view post
Post
691
Hello!
The 8B/70B OG Llama-3 models made with the Orthogonal Activation Steering script as been pushed in private.

After multiple test with an empty prompt system, I can confirm it's not uncensored enough, but I wanted to try all the GGUF before (and it take time to do lmao)

If you want to try that yourself, here is the script : https://gist.github.com/wassname/42aba7168bb83e278fcfea87e70fa3af
And here is the same script that we modified to be able to use it on multiple GPU for 70B : https://files.catbox.moe/ya4rto.ipynb

Llama3-Unholy-8B-OAS don't have the problem as it was already trained to be less censored, but the OG one was really too much censored.

I will try to redo that soon, as it seems to HAVE WORKED for some prompt (as seen on the log, for exemple) but it's not enough.

32 entry of the dataset is clearly not enough, but it's okay, I really wanted to try that as it was something new.
I could take the Unholy way and retrain the 70B before using OAS but it should work without, that's not the goal.
Β·
not-lainΒ 
posted an update about 11 hours ago
albertvillanovaΒ 
posted an update about 12 hours ago
view post
Post
317
πŸš€ We recently released datasets 2.19.0! πŸ“¦

πŸ”₯ What's New:
- Polars integration πŸ»β€β„οΈ
- fsspec support for conversion to JSON, CSV, and Parquet
- Mode parameter for Image feature
- CLI function to convert script-datasets to Parquet
- Dataset.take and Dataset.skip

Plus, a bunch of general improvements & bug fixes!

Check out the release notes: https://github.com/huggingface/datasets/releases/tag/2.19.0

Upgrade now and power up your data workflows! πŸ’₯
  • 2 replies
Β·
SeverianΒ 
posted an update about 13 hours ago
Recently active users