hf-carbon/sft_Qwen3-4B_simple_qa
Text Generation
•
0.6B
•
Updated
•
86
AI & ML interests
None defined yet.
Recent Activity
View all activity
cgeorgiaw
updated
a
model
1 day ago
Post
1381
🚀🚀🚀Huge biotech data drop today🚀🚀🚀
The largest drug-target dataset ever created was just released on Hugging Face—and it's still growing...
EvE Bio is further updating the dataset every 8 weeks. Drug development dream.
Read the blog: https://huggingface.co/blog/hugging-science/eve-bio-mapping-the-pharmone-drug-interaction
Play with the data: eve-bio/drug-target-activity
The largest drug-target dataset ever created was just released on Hugging Face—and it's still growing...
EvE Bio is further updating the dataset every 8 weeks. Drug development dream.
Read the blog: https://huggingface.co/blog/hugging-science/eve-bio-mapping-the-pharmone-drug-interaction
Play with the data: eve-bio/drug-target-activity
abidlabs
authored
3
papers
about 2 months ago
Post
8975
Why I think local, open-source models will eventually win.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
The most useful AI applications are moving toward multi-turn agentic behavior: systems that take hundreds or even thousands of iterative steps to complete a task, e.g. Claude Code, computer-control agents that click, type, and test repeatedly.
In these cases, the power of the model is not how smart it is per token, but in how quickly it can interact with its environment and tools across many steps. In that regime, model quality becomes secondary to latency.
An open-source model that can call tools quickly, check that the right thing was clicked, or verify that a code change actually passes tests can easily outperform a slightly “smarter” closed model that has to make remote API calls for every move.
Eventually, the balance tips: it becomes impractical for an agent to rely on remote inference for every micro-action. Just as no one would tolerate a keyboard that required a network request per keystroke, users won’t accept agent workflows bottlenecked by latency. All devices will ship with local, open-source models that are “good enough” and the expectation will shift toward everything running locally. It’ll happen sooner than most people think.
- 8 replies
lvwerra
authored
a
paper
3 months ago
Post
1558
What other features would you like to see on the Trackio Dashboard? (
gradio-templates/trackio-dashboard)
Post
5988
🚀🚀🚀 The largest ever dataset of co-folded 3D protein-ligand structures just dropped on HF!!
Meet SAIR (Structurally Augmented IC₅₀ Repository): 5M+ AI-generated complexes with experimentally measured drug potency data from SandboxAQ. 🚀🚀🚀
Check it out and explore here: SandboxAQ/SAIR
Meet SAIR (Structurally Augmented IC₅₀ Repository): 5M+ AI-generated complexes with experimentally measured drug potency data from SandboxAQ. 🚀🚀🚀
Check it out and explore here: SandboxAQ/SAIR
-
- 3 replies
Post
637
Just dropped the most influential materials science data of the year so far! Check it out :)))
cgeorgiaw/WyFormer-Symmetric-Crystals
cgeorgiaw/WyFormer-Symmetric-Crystals
- 1 reply
lvwerra
authored
a
paper
7 months ago
guipenedo
authored
a
paper
7 months ago
Post
2791
Huge new bio datasets just dropped!!!
Check out them out @
ginkgo-datapoints
Read the blog for more info: https://huggingface.co/blog/cgeorgiaw/gdp
Check out them out @
Read the blog for more info: https://huggingface.co/blog/cgeorgiaw/gdp
- 1 reply
Post
1615
Snooping on HF is the best because sometimes you just discover that someone (in this case, Earth Species Project) is about to drop terabytes of sick (high quality animal sounds) data...
EarthSpeciesProject/NatureLM-audio-training
EarthSpeciesProject/NatureLM-audio-training
loubnabnl
authored
a
paper
7 months ago
guipenedo
authored
a
paper
7 months ago
Post
4483
The Gradio x Agents x MCP hackathon keeps growing! We now have more $1,000,000 in credit for participants and and >$16,000 in cash prizes for winners.
We've kept registration open until the end of this week, so join and let's build cool stuff together as a community: https://huggingface.co/spaces/ysharma/gradio-hackathon-registration-2025
We've kept registration open until the end of this week, so join and let's build cool stuff together as a community: https://huggingface.co/spaces/ysharma/gradio-hackathon-registration-2025
Post
527
Just dropped two bigger physics datasets (both on photonics)!
NUMBA 1: SIB-CL
This dataset of Surrogate- and Invariance-Boosted Contrastive Learning (SIB-CL) datasets for two scientific problems:
- PhC2D: 2D photonic crystal density-of-states (DOS) and bandstructure data.
- TISE: 3D time-independent Schrödinger equation eigenvalue and eigenvector solutions.
NUMBA2: 2D Photonic Topology
Symmetry-driven analysis of 2D photonic crystals: 10k random unit cells across 11 symmetries, 2 polarizations, 5 contrasts. Includes time-reversal breaking cases for 4 symmetries at high contrast.
Check them out: cgeorgiaw/sib-cl & cgeorgiaw/2d-photonic-topology
NUMBA 1: SIB-CL
This dataset of Surrogate- and Invariance-Boosted Contrastive Learning (SIB-CL) datasets for two scientific problems:
- PhC2D: 2D photonic crystal density-of-states (DOS) and bandstructure data.
- TISE: 3D time-independent Schrödinger equation eigenvalue and eigenvector solutions.
NUMBA2: 2D Photonic Topology
Symmetry-driven analysis of 2D photonic crystals: 10k random unit cells across 11 symmetries, 2 polarizations, 5 contrasts. Includes time-reversal breaking cases for 4 symmetries at high contrast.
Check them out: cgeorgiaw/sib-cl & cgeorgiaw/2d-photonic-topology
cgeorgiaw
authored
2
papers
8 months ago