Spaces for Image-to-Image / Video
Collection
617 items
โข
Updated
โข
41
John Smith PRO
John6666
AI & ML interests
None yet
Recent Activity
updated
a collection
about 3 hours ago
Spaces for Image-to-Image / Video
liked
a Space
about 3 hours ago
linoyts/Qwen-Image-Edit-2511-Fast
liked
a model
about 4 hours ago
Vortex5/Moonlit-Umbra-12B
Organizations
updated
a
collection
about 3 hours ago
liked
a
Space
about 3 hours ago
liked
11
models
about 4 hours ago
Vortex5/Moonlit-Umbra-12B
Text Generation
โข
12B
โข
Updated
โข
138
โข
4
mradermacher/Moonlit-Umbra-12B-i1-GGUF
12B
โข
Updated
โข
3.55k
โข
1
mradermacher/Moonlit-Umbra-12B-GGUF
12B
โข
Updated
โข
640
โข
2
Zaynoid/Qwen3-VL-8B-V5
Image-to-Text
โข
9B
โข
Updated
โข
23
โข
1
mradermacher/Qwen3-VL-8B-V5-i1-GGUF
8B
โข
Updated
โข
1.12k
โข
1
mradermacher/Qwen3-VL-8B-V5-GGUF
8B
โข
Updated
โข
350
โข
1
Zaynoid/Qwen3-VL-8B-V6
Image-to-Text
โข
9B
โข
Updated
โข
41
โข
1
mradermacher/Qwen3-VL-8B-V6-i1-GGUF
8B
โข
Updated
โข
1.2k
โข
1
mradermacher/Qwen3-VL-8B-V6-GGUF
8B
โข
Updated
โข
378
โข
1
Chinastark/ATK-3B
3B
โข
Updated
โข
14
โข
1
mradermacher/ATK-3B-GGUF
3B
โข
Updated
โข
233
โข
1
updated
a
collection
about 9 hours ago
liked
a
Space
about 9 hours ago
upvoted
a
collection
about 9 hours ago
reacted to
ibragim-bad's
post with ๐
about 9 hours ago
Post
155
๐ 67,074 Qwen3-Coder OpenHands trajectories + 2 RFT checkpoints.
We release: 67,000+ trajectories from 3,800 resolved issues in 1,800+ Python repos.
About 3x more successful trajectories and 1.5x more repos than our previous dataset.
Trajectories are long: on average 64 turns, up to 100 turns and 131k context length.
> RFT on this data, SWE-bench Verified:
Qwen3-30B-Instruct: 25.7% โ 50.3% Pass@1.
Qwen3-235B-Instruct: 46.2% โ 61.7% Pass@1.
Also strong gains on SWE-rebench September.
> We also did massive evals.
We run OpenHands with 100 and 500 turns.
We compare models under both limits.
We run on SWE-bench Verified and several months of SWE-rebench.
!!! We also check tests written by the models.
We measure how often tests are correct.
We check how often the final patch passes its own tests.
This gives a pool of tests for verifiers and auto graders.
> Fully permissive licenses
Dataset and models: https://huggingface.co/collections/nebius/openhands-trajectories
Blog post: https://nebius.ai/blog/posts/openhands-trajectories-with-qwen3-instruct
We release: 67,000+ trajectories from 3,800 resolved issues in 1,800+ Python repos.
About 3x more successful trajectories and 1.5x more repos than our previous dataset.
Trajectories are long: on average 64 turns, up to 100 turns and 131k context length.
> RFT on this data, SWE-bench Verified:
Qwen3-30B-Instruct: 25.7% โ 50.3% Pass@1.
Qwen3-235B-Instruct: 46.2% โ 61.7% Pass@1.
Also strong gains on SWE-rebench September.
> We also did massive evals.
We run OpenHands with 100 and 500 turns.
We compare models under both limits.
We run on SWE-bench Verified and several months of SWE-rebench.
!!! We also check tests written by the models.
We measure how often tests are correct.
We check how often the final patch passes its own tests.
This gives a pool of tests for verifiers and auto graders.
> Fully permissive licenses
Dataset and models: https://huggingface.co/collections/nebius/openhands-trajectories
Blog post: https://nebius.ai/blog/posts/openhands-trajectories-with-qwen3-instruct
- 1 reply
reacted to
AbstractPhil's
post with ๐
about 9 hours ago
Post
129
geofractal getting started guide available, bulk ablation for fusion, simple towers, oscillator capacity, and substructure systemic associative capacity.
Many formulas were tested, 92 tests for collectives, oscillation bulk experiments, and more. All of them either coalesce into the correct behavior or the failures are directly visible, which means the system is robust enough to declare some tools functionally valid but not scalable yet.
ai-crash course available;
https://github.com/AbstractEyes/geofractal/blob/main/ai_helpers/v101_claude_helpers.txt
Feed GPT, Claude, or Grokk and they will assist.
getting started guide;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/GETTING_STARTED.md
geofractal router architecture is in prototype phases;
https://github.com/AbstractEyes/geofractal
This is likely one of it's final growing phases before full production capacity is ramped up. The architecture is not for the novice, it's meant for experts to either get ideas, borrow code, utilize library capacity, or simply tell AI what to do. MOST files in current production have good descriptions for AI integration.
Transfer learning notebook available here;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/Router_Transfer_Learning-12_19_25.ipynb
Stress test and multiple diagnostics available here;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/components/diagnostics/
WideRouter compilation capacity available;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/wide_router.py
The wide router compiler organizes similar towers into stacked staged combinations before compiling with torch.compile. This is experimental, but has shown increased speed with multiple structures of wide models and will serve it's purpose in the future.
Many formulas were tested, 92 tests for collectives, oscillation bulk experiments, and more. All of them either coalesce into the correct behavior or the failures are directly visible, which means the system is robust enough to declare some tools functionally valid but not scalable yet.
ai-crash course available;
https://github.com/AbstractEyes/geofractal/blob/main/ai_helpers/v101_claude_helpers.txt
Feed GPT, Claude, or Grokk and they will assist.
getting started guide;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/GETTING_STARTED.md
geofractal router architecture is in prototype phases;
https://github.com/AbstractEyes/geofractal
This is likely one of it's final growing phases before full production capacity is ramped up. The architecture is not for the novice, it's meant for experts to either get ideas, borrow code, utilize library capacity, or simply tell AI what to do. MOST files in current production have good descriptions for AI integration.
Transfer learning notebook available here;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/Router_Transfer_Learning-12_19_25.ipynb
Stress test and multiple diagnostics available here;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/components/diagnostics/
WideRouter compilation capacity available;
https://github.com/AbstractEyes/geofractal/blob/main/src/geofractal/router/wide_router.py
The wide router compiler organizes similar towers into stacked staged combinations before compiling with torch.compile. This is experimental, but has shown increased speed with multiple structures of wide models and will serve it's purpose in the future.
- 1 reply
reacted to
TravisMuhlestein's
post with ๐
about 9 hours ago
Post
107
From AI demos to production systems: what breaks when agents become autonomous?
A recurring lesson from production AI deployments is that most failures are system failures, not model failures.
As organizations move beyond pilots, challenges increasingly shift toward:
โข Agent identity and permissioning
โข Trust boundaries between agents and human operators
โข Governance and auditability for autonomous actions
โข Security treated as a first-class architectural constraint
This recent Fortune article highlights how enterprises are navigating that transition, including work with AWSโs AI Innovation Lab.
Open question for the community:
What architectural patterns or tooling are proving effective for managing identity, permissions, and safety in autonomous or semi-autonomous agent systems in production?
Context: https://fortune.com/2025/12/19/amazon-aws-innovation-lab-aiq/
A recurring lesson from production AI deployments is that most failures are system failures, not model failures.
As organizations move beyond pilots, challenges increasingly shift toward:
โข Agent identity and permissioning
โข Trust boundaries between agents and human operators
โข Governance and auditability for autonomous actions
โข Security treated as a first-class architectural constraint
This recent Fortune article highlights how enterprises are navigating that transition, including work with AWSโs AI Innovation Lab.
Open question for the community:
What architectural patterns or tooling are proving effective for managing identity, permissions, and safety in autonomous or semi-autonomous agent systems in production?
Context: https://fortune.com/2025/12/19/amazon-aws-innovation-lab-aiq/
reacted to
ronantakizawa's
post with ๐
about 9 hours ago
Post
647
Thank you
@clem
(Co-Founder & CEO of Hugging Face) for sharing my dataset on X / Twitter!
ronantakizawa/github-top-developers
#github #dataset
ronantakizawa/github-top-developers
#github #dataset
-
- 1 reply