Hugging Face's logo

nltpt-q
community
Activity Feed

AI & ML interests

None defined yet.
ariG23498 
posted an update 24 days ago
cfahlgren1 
posted an update about 2 months ago
view post
Post
432
I ran the Anthropic Misalignment Framework for a few top models and added it to a dataset: cfahlgren1/anthropic-agentic-misalignment-results

You can read the reasoning traces of the models trying to blackmail the user and perform other actions. It's very interesting!!
reach-vb 
posted an update 2 months ago
view post
Post
3957
Excited to onboard FeatherlessAI on Hugging Face as an Inference Provider - they bring a fleet of 6,700+ LLMs on-demand on the Hugging Face Hub 🤯

Starting today, you'd be able to access all those LLMs (OpenAI compatible) on HF model pages and via OpenAI client libraries too! 💥

Go, play with it today: https://huggingface.co/blog/inference-providers-featherless

P.S. They're also bringing on more GPUs to support all your concurrent requests!
  • 1 reply
·
ariG23498 
posted an update 2 months ago
view post
Post
1699
🚨 Implement KV Cache from scratch in pure PyTorch. 🚨

We have documented all of our learning while implementing KV Cache to nanoVLM. Joint work with @kashif @lusxvr @andito @pcuenq

Blog: hf.co/blog/kv-cache
  • 1 reply
·
cfahlgren1 
posted an update 2 months ago
cfahlgren1 
posted an update 3 months ago
reach-vb 
posted an update 3 months ago
view post
Post
4234
hey hey @mradermacher - VB from Hugging Face here, we'd love to onboard you over to our optimised xet backend! 💥

as you know we're in the process of upgrading our storage backend to xet (which helps us scale and offer blazingly fast upload/ download speeds too): https://huggingface.co/blog/xet-on-the-hub and now that we are certain that the backend can scale with even big models like Llama 4/ Qwen 3 - we;re moving to the next phase of inviting impactful orgs and users on the hub over as you are a big part of the open source ML community - we would love to onboard you next and create some excitement about it in the community too!

in terms of actual steps - it should be as simple as one of the org admins to join hf.co/join/xet - we'll take care of the rest.

p.s. you'd need to have a the latest hf_xet version of huggingface_hub lib but everything else should be the same: https://huggingface.co/docs/hub/storage-backends#using-xet-storage

p.p.s. this is fully backwards compatible so everything will work as it should! 🤗
·
pcuenq 
authored a paper 4 months ago
reach-vb 
authored a paper 4 months ago
cfahlgren1 
authored a paper 6 months ago
reach-vb 
authored a paper 6 months ago
cfahlgren1 
posted an update 7 months ago
view post
Post
2346
If you haven't seen yet, we just released Inference Providers 🔀

> 4 new serverless inference providers on the Hub 🤯
> Use your HF API key or personal key with all providers 🔑
> Chat with Deepseek R1, V3, and more on HF Hub 🐋
> We support Sambanova, TogetherAI, Replicate, and Fal.ai 💪

Best of all, we don't charge any markup on top of the provider 🫰 Have you tried it out yet? HF Pro accounts get $2 of free usage for the provider inference.
ariG23498 
posted an update 7 months ago
ariG23498 
posted an update 7 months ago
cfahlgren1 
posted an update 7 months ago
view post
Post
1780
Wow, I just added Langfuse tracing to the Deepseek Artifacts app and it's really nice 🔥

It allows me to visualize and track more things along with the cfahlgren1/react-code-instructions dataset.

It was just added as a one click Docker Space template, so it's super easy to self host 💪
cfahlgren1 
posted an update 7 months ago
view post
Post
2268
You'll notice the AI in the SQL Console is much better at working with chatml conversations:

Here's example of unnesting the cfahlgren1/react-code-instructions in less than 10 seconds by asking it. Check it out here: cfahlgren1/react-code-instructions

- "show me the average assistant response length"
- "extract user, system, and assistant messages into separate columns"

It's super easy to work with conversational datasets now with natural language 🗣️





  • 2 replies
·
cfahlgren1 
posted an update 8 months ago
reach-vb 
posted an update 8 months ago
view post
Post
7160
VLMs are going through quite an open revolution AND on-device friendly sizes:

1. Google DeepMind w/ PaliGemma2 - 3B, 10B & 28B: google/paligemma-2-release-67500e1e1dbfdd4dee27ba48

2. OpenGVLabs w/ InternVL 2.5 - 1B, 2B, 4B, 8B, 26B, 38B & 78B: https://huggingface.co/collections/OpenGVLab/internvl-25-673e1019b66e2218f68d7c1c

3. Qwen w/ Qwen 2 VL - 2B, 7B & 72B: Qwen/qwen2-vl-66cee7455501d7126940800d

4. Microsoft w/ FlorenceVL - 3B & 8B: @jiuhai

5. Moondream2 w/ 0.5B: https://huggingface.co/vikhyatk/

What a time to be alive! 🔥
ariG23498 
posted an update 8 months ago
cfahlgren1 
posted an update 8 months ago
view post
Post
1941
You can just ask things 🗣️

"show me messages in the coding category that are in the top 10% of reward model scores"

Download really high quality instructions from the Llama3.1 405B synthetic dataset 🔥

argilla/magpie-ultra-v1.0