Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up

All HF Hub posts
ajibawa-2023 
posted an update 1 day ago
view post
Post
4564
Shell-Code-Large
Dataset: ajibawa-2023/Shell-Code-Large

Shell-Code-Large is a large-scale corpus of Shell scripting source code comprising approximately 640,000 code samples stored in JSON Lines (.jsonl) format. The dataset is designed to support research in large language model (LLM) pretraining, code intelligence, DevOps automation, cloud infrastructure engineering, system administration, and software engineering automation.

By providing a high-volume, language-specific corpus focused exclusively on Shell scripting, Shell-Code-Large enables systematic experimentation in automation workflows, deployment pipelines, infrastructure management, and command-line tooling. These domains remain foundational to Linux systems, cloud-native platforms, CI/CD environments, and modern DevOps practices.

Shell-Code-Large addresses the need for a dedicated Shell-focused dataset at substantial scale, enabling targeted research into scripting patterns, command composition, workflow orchestration, infrastructure automation, and operational engineering practices
Reubencf 
posted an update 3 days ago
view post
Post
3574
Shadows of Tomorrow is finally live on Hugging Face Spaces with Gradio.

It’s a browser-playable RPG built with Godot, set in a post-nuclear future where players explore Magnus Province, collect medicinal plants, craft medicine, and help cure NPCs.

Play it here: Reubencf/Shadows_of_Tomorrow
  • 10 replies
·
dronefreak 
posted an update 3 days ago
view post
Post
2917
Excited to open-source the VisDrone Aerial Object Detection Model Zoo on Hugging Face.

The collection includes multiple YOLO variants trained and evaluated on the VisDrone benchmark for aerial object detection, with accompanying documentation and performance metrics.

If you're working on drones, aerial surveillance, robotics, or small-object detection, I hope these models save you some time.

Model Zoo: https://huggingface.co/collections/dronefreak/visdrone-detection-model-zoo

Feedback, issues, and contributions are welcome.
  • 5 replies
·
AxionLab-official 
posted an update 3 days ago
view post
Post
3287
# An Open Letter from SupraLabs.

Over the past few days, SupraLabs has been mentioned in a public discussion regarding small language models, scaling laws, and training methodology. We'd like to clarify our position.

Before anything else, we want to make one thing absolutely clear: we have great respect for Lane and the work being done at Glint Research. At no point was our intention to disrespect Lane, Glint Research, or their research. What began as a technical discussion about model scaling and training methodology unfortunately became much more personal than we ever intended. From our perspective, it was simply an exchange of technical opinions, and we sincerely hope it remains that way.
We'd also like to acknowledge that one of our own comments during the discussion was poorly worded. Referring to a benchmark as "fake" was imprecise. What we intended to criticize was the comparison methodology, not the integrity of the evaluation itself. Comparing a merged checkpoint against a single checkpoint is, in our view, not an apples-to-apples comparison.

That said, this was never the core of the discussion.

Our disagreement was not about SLERP, model merging, or whether training a small model on massive amounts of data is an interesting research direction. We support experimentation and unconventional ideas.

The actual point of disagreement was much simpler.

The statement that a 1M parameter model trained on 1 trillion tokens will become a "100M killer" is, today, a prediction, not an experimental result.
Could it happen? Perhaps.
Would it be exciting if it did? Absolutely.

But until benchmark results, reproducible evaluations, and independent validation exist, we believe such statements should be presented as hypotheses rather than established conclusions.
Research advances by testing ideas, not by assuming their outcomes.

We sincerely wish Lane and everyone at Glint Research success in their experiments.

Thank you to everyone who read it.
  • 1 reply
·
AxionLab-official 
posted an update about 22 hours ago
Anran-MLLM 
posted an update 3 days ago
view post
Post
3423
🚀 Introducing PerceptionDLM — the first multimodal diffusion LLM for parallel region perception!

Most MLLMs are autoregressive, so captioning N regions costs N sequential passes. PerceptionDLM instead describes ALL masked regions in a single denoising process. 🧩

✨ Highlights
• ⚡ Up to 3.4× faster on dense multi-region captioning, with stable per-image latency
• 🏆 PerceptionDLM-Base beats LLaDA-V on 15/16 multimodal benchmarks (new SOTA among open diffusion VLMs)
• 📊 New benchmark: ParaDLC-Bench — jointly evaluates caption quality AND inference efficiency
• 🔓 Code, models & benchmark all open-sourced

🤖 Models
MSALab/PerceptionDLM-Base
MSALab/PerceptionDLM

📊 Benchmark
MSALab/ParaDLC-Bench

📄 Paper: PerceptionDLM: Parallel Region Perception with Multimodal Diffusion Language Models (2606.19534)
💻 Code: https://github.com/MSALab-PKU/PerceptionDLM

Diffusion LLMs aren't just for text — they unlock efficient, parallel visual perception. 👁️✨

#multimodal #diffusion #VLM #perception
kanaria007 
posted an update 2 days ago
view post
Post
159
✅ Article highlight: *Embodied SI-Core: Observation, Homeostasis, Reflexes, and Safe Actuation* (art-60-178, v0.1)

TL;DR:
This article argues that SI-Core does not stop at text, tools, or simulated policy.

Once a system can sense, self-regulate, react, and actuate, governance must reach the sensing and motion boundary. Embodied SI-Core keeps observation, ethics, rollback, memory, and evaluation alive across perception, internal state, reflex paths, and actuator-safe execution.

Read:
kanaria007/agi-structural-intelligence-protocols

Why it matters:
• treats perception and actuation as governed runtime surfaces
• keeps fast reflex paths inside bounded ethics and rollback discipline
• makes internal state part of routing, not just telemetry
• blocks under-observed motion from becoming a world effect
• connects robots, avatars, vehicles, prosthetics, edge devices, and simulated actors under one frame

What’s inside:
• embodied observation bundles with coverage and confidence
• HOMEODYNA-style internal-state tension and jump suppression
• REFLEXIA-style bounded low-latency reflex routing
• KINETICA-style intent-to-actuation planning
• execution monitoring, safe-stop, rollback, and reentry logs
• an embodied runtime arc from raw sensory inputs to append-only memory

Key idea:
Do not say:

*“the agent saw something and acted.”*

Say:

*“this embodied system parsed the observation, checked internal-state tension, selected a governed route, bound action through ethics and reversibility, monitored execution, and reentered memory with receipts.”*

Sense structurally.
Regulate internally.
React only within bounds.
Actuate with receipts.
AmelieSchreiber 
posted an update 2 days ago
view post
Post
1958
Latest OpenAI Parameter Golf Competition Training Run BPB (<1K steps on a single 4090) See: ToricBLM, ToricGT, and TropicalGT methods
  • 1 reply
·
Hari5115 
posted an update 3 days ago
view post
Post
1460
Bit addictive. Fair warning !!!
Chain combos, fever mode, daily leaderboard. Free, runs in your browser.
Beat the score if you can 🫧

🎮 Hari5115/neon-pop

#SendHelp #JustOneMoreGame #NeonPop #NotAddicted

  • 2 replies
·
legolasyiu 
posted an update 4 days ago
view post
Post
110
Introducing Reasoning-Medical-27B is designed for advanced medical reasoning in professional medicine, medical genetics, college biology/medicine, and clinical knowledge. The model was fine-tuned on a large-scale dataset of 370,000 high-quality question-and-answer examples, incorporating Chain-of-Thought reasoning to improve step-by-step problem solving. Training was performed using the GRPO trainer with the Unsloth optimization method for efficient fine-tuning.
MedQA: 93% vs MedGemma 85.3%

Model: EpistemeAI/Reasoning-Medical-27B



# Benchmark

| Task              | Version | Filter         | n-shot | Metric      | Direction | Reasoning Medical 27B | Qwen 3.6 27B | MedGemma 1 27B |
|-------------------|--------:|----------------|-------:|-------------|:---------:|----------------------:|-------------:|----------------:|
| MMLU-Pro Biology  | 3.1     | custom-extract | 2      | exact_match | ↑         | 0.85                  | —            | —               |
| MMLU-ProX Biology | 0       | custom-extract | 2      | exact_match | ↑         | 0.80                  | —            | —               |
| MedQA             | YAML    | none           | 2      | acc         | ↑         | 0.93                  | 0.844        | 0.853           |

Recently active users