Robot-Learning-Collective/VLA-0-Smol
Robotics
•
Updated
•
91
•
2
Ibragim
ibragim-bad
AI & ML interests
Data for code agents
Recent Activity
liked
a model
2 days ago
Robot-Learning-Collective/VLA-0-Smol
liked
a dataset
2 days ago
Puzer/github-repo-embeddings
new activity
2 days ago
ibragim-bad/github-repos-metadata-40M:Sharing a complementary dataset with repository embeddings
Organizations
liked
a
model
2 days ago
liked
a
dataset
2 days ago
Sharing a complementary dataset with repository embeddings
🔥
1
1
#2 opened 2 days ago
by
Puzer
updated
a
dataset
2 days ago
liked
a
model
9 days ago
updated
2
datasets
15 days ago
posted
an
update
15 days ago
Post
332
🎄 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% → 50.3% Pass@1.
Qwen3-235B-Instruct: 46.2% → 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% → 50.3% Pass@1.
Qwen3-235B-Instruct: 46.2% → 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
- 2 replies
published
2
models
15 days ago
updated
2
models
15 days ago
updated
a
dataset
15 days ago
upvoted
a
paper
about 1 month ago
updated
a
dataset
about 2 months ago
How can I find all instance_ids that come with a Docker image?
4
#10 opened 3 months ago
by
KYLN24
published
a
dataset
2 months ago
liked
a
model
3 months ago
updated
a
dataset
3 months ago
published
a
dataset
3 months ago