paperweight

community
Activity Feed

AI & ML interests

purpose built small models

Recent Activity

cfahlgren1  updated a Space 3 days ago
paperweight/tinyfix
cfahlgren1  published a Space 3 days ago
paperweight/tinyfix
cfahlgren1  updated a Space 3 days ago
paperweight/offline-page
View all activity

cfahlgren1 
updated a Space 4 days ago
cfahlgren1 
posted an update over 1 year ago
view post
Post
2,188
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!!

cfahlgren1 
posted an update over 1 year ago
cfahlgren1 
posted an update over 1 year ago
cfahlgren1 
posted an update almost 2 years ago
view post
Post
2,360
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.
cfahlgren1 
posted an update almost 2 years ago
view post
Post
1,802
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 almost 2 years ago
view post
Post
2,288
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 almost 2 years ago
cfahlgren1 
posted an update almost 2 years ago
view post
Post
1,952
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

cfahlgren1 
posted an update almost 2 years ago
view post
Post
3,100
We just dropped an LLM inside the SQL Console 🤯

The amazing, new Qwen/Qwen2.5-Coder-32B-Instruct model can now write SQL for any Hugging Face dataset ✨

It's 2025, you shouldn't be hand writing SQL! This is a big step in making it where anyone can do in depth analysis on a dataset. Let us know what you think 🤗