Post
83
kinda ridiculous making "cpu-basic" paid and "ZeroGPU" is free but 2 spaces for free user.
i'm confused dawg
i'm confused dawg
π‘ i hate it
Rico Ardiansyah
R-Kentaren
AI & ML interests
frontend
Recent Activity
updated a Space about 3 hours ago
R-Kentaren/MiniCPM5-1B-Demo posted an update about 20 hours ago
kinda ridiculous making "cpu-basic" paid and "ZeroGPU" is free but 2 spaces for free user.
i'm confused dawg updated a Space about 21 hours ago
R-Kentaren/ace-step-jamOrganizations
posted an update about 20 hours ago
reacted to KingNish's post with π about 1 month ago
Post
4574
We trained an open-source Mythos like cybersecurity LLM for the Build Small Hackathon meet OpenMythos
Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth.
Trained on: H100s from Modal
The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes.
Everything is open:
π€ Demo β build-small-hackathon/OpenMythos
π§ Model β build-small-hackathon/OpenMythos
π¦ CVE Dataset β build-small-hackathon/CVE_Vulnerailities_Detailed
π ArXiv Dataset β himanshu17HF/ArvixImport-Filtered-Final
Try it out and let us know where it breaks π
Trained in two stages: SFT on ~1.84K filtered ArXiv cs.CR papers + real CVE data, then RLVR using paired with past vulnerabilities GitHub repos with a verifier model checking outputs against ground truth.
Trained on: H100s from Modal
The RLVR stage made the biggest difference responses got more precise and less prone to confusing similar vulnerability classes.
Everything is open:
π€ Demo β build-small-hackathon/OpenMythos
π§ Model β build-small-hackathon/OpenMythos
π¦ CVE Dataset β build-small-hackathon/CVE_Vulnerailities_Detailed
π ArXiv Dataset β himanshu17HF/ArvixImport-Filtered-Final
Try it out and let us know where it breaks π
- 2 replies
reacted to danielhanchen's post with β€οΈ 2 months ago
Post
5998
Weβre excited to announce that Unsloth has joined the PyTorch Ecosystem! π₯π¦₯
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! π
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
Unsloth is an open-source project that makes training & running models more accurate and faster with less compute. Our mission is to make local AI accessible to everyone. Thanks to all of you for making this possible! π
Blog: https://unsloth.ai/blog/pytorch
GitHub: https://github.com/unslothai/unsloth
- 2 replies
reacted to qgallouedec's post with π₯ 3 months ago
Post
10589
Shipped hf-sandbox! π₯‘
π§ͺ Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
π https://github.com/huggingface/hf-sandbox
π§ͺ Running an eval that executes model-generated C on a few thousand prompts? You probably don't want any of that on your laptop.
Just shipped hf-sandbox, a Modal-style sandbox API on top of Hugging Face Jobs. Spin up an isolated, ephemeral container, run untrusted code, get the result back. No Docker on your laptop, no infra to manage.
Just pip install hf-sandbox.
Early days (v0.1); feedback and issues very welcome:
π https://github.com/huggingface/hf-sandbox
- 1 reply
reacted to evalstate's post with π€ 3 months ago
Post
2227
Hugging Face MCP Server v0.3.12
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The hub_repo_details tool now enables Dataset inspection (view splits, sample rows).
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
The hub_repo_details tool now enables Dataset inspection (view splits, sample rows).
reacted to sequelbox's post with β€οΈ 3 months ago
Post
3354
EARLY SNEAK PREVIEW of our first DeepSeek-V4-Pro dataset, Tachibana 4!
Tachibana 4 is our upcoming agentic coding dataset:
- Questions prioritize real-world, challenging agentic coding tasks across a variety of programming languages and topics.
- Areas of focus include back-end and front-end development, systems programming, distributed systems, performance optimization, data structures, databases and data engineering, game and mobile development, security engineering, compiler design, custom tooling, task automation, practical bugfixes, and more!
- A wide variety of emphasized languages improves development capability: Python, C, C++, C#, Go, TypeScript, Java, JavaScript, Rust, Haskell, SQL, Shell, R, Ruby, assembly code, and more!
- Synthethic prompts utilize a variety of personas, experience levels, and styles of communication to maximize real-world flexibility and usability.
Get it now: sequelbox/Tachibana4-DeepSeek-V4-Pro-PREVIEW
These agentic datasets will power the upcoming Esper 4, and whatever you can build! We'll have more finetunes on the way as well! :) we're going to make open source better and better for your work!
If you would like to see Esper 4 and these datasets faster, this is the best way you can help us: sequelbox/SupportOpenSource
for freedom, with love,
allegra
Tachibana 4 is our upcoming agentic coding dataset:
- Questions prioritize real-world, challenging agentic coding tasks across a variety of programming languages and topics.
- Areas of focus include back-end and front-end development, systems programming, distributed systems, performance optimization, data structures, databases and data engineering, game and mobile development, security engineering, compiler design, custom tooling, task automation, practical bugfixes, and more!
- A wide variety of emphasized languages improves development capability: Python, C, C++, C#, Go, TypeScript, Java, JavaScript, Rust, Haskell, SQL, Shell, R, Ruby, assembly code, and more!
- Synthethic prompts utilize a variety of personas, experience levels, and styles of communication to maximize real-world flexibility and usability.
Get it now: sequelbox/Tachibana4-DeepSeek-V4-Pro-PREVIEW
These agentic datasets will power the upcoming Esper 4, and whatever you can build! We'll have more finetunes on the way as well! :) we're going to make open source better and better for your work!
If you would like to see Esper 4 and these datasets faster, this is the best way you can help us: sequelbox/SupportOpenSource
for freedom, with love,
allegra
reacted to danielhanchen's post with π€ 3 months ago
reacted to danielhanchen's post with ππ₯ 4 months ago
Post
5581
You can now fine-tune Gemma 4 for free with our notebooks! π₯
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
You just need 8GB VRAM to train Gemma 4 locally!
Unsloth trains Gemma4 1.5x faster with 50% less VRAM.
GitHub: https://github.com/unslothai/unsloth
Guide + Notebooks: https://unsloth.ai/docs/models/gemma-4/train
- 5 replies
reacted to gokaygokay's post with π₯ 9 months ago
Post
9420
FlashPack: Lightning-Fast Model Loading for PyTorch
https://github.com/fal-ai/flashpack
FlashPack β a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS).
With FlashPack, loading any model can be 3β6Γ faster than with the current state-of-the-art methods like accelerate or the standard load_state_dict() and to() flow β all wrapped in a lightweight, pure-Python package that works anywhere.
https://github.com/fal-ai/flashpack
FlashPack β a new, high-throughput file format and loading mechanism for PyTorch that makes model checkpoint I/O blazingly fast, even on systems without access to GPU Direct Storage (GDS).
With FlashPack, loading any model can be 3β6Γ faster than with the current state-of-the-art methods like accelerate or the standard load_state_dict() and to() flow β all wrapped in a lightweight, pure-Python package that works anywhere.
- 3 replies
reacted to prithivMLmods's post with π₯ 10 months ago
Post
4570
Try the Hugging Face Space demo for Logics-MLLM/Logics-Parsing, the latest multimodal VLM from the Logics Team at Alibaba Group. It enables end-to-end document parsing with precise content extraction in markdown format, and it also generates a clean HTML representation of the document while preserving its logical structure. π€π₯
Additionally, Iβve integrated one of my recent works β prithivMLmods/Gliese-OCR-7B-Post1.0 β which also excels at document comprehension.
β Space / App : prithivMLmods/VLM-Parsing
π Technical Report by the Logics Team, Alibaba Group : Logics-Parsing Technical Report (2509.19760)
π MM: VLM-Parsing: prithivMLmods/mm-vlm-parsing-68e33e52bfb9ae60b50602dc
β‘ Collections : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
Other Pages:
β Multimodal VLMs - July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
β Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd
β VL caption β < Sep 15 β25 : prithivMLmods/vl-caption-sep-15-25-68c7f6d737985c63c13e2391
.
.
.
To know more about it, visit the app page or the respective model page!!
Additionally, Iβve integrated one of my recent works β prithivMLmods/Gliese-OCR-7B-Post1.0 β which also excels at document comprehension.
β Space / App : prithivMLmods/VLM-Parsing
π Technical Report by the Logics Team, Alibaba Group : Logics-Parsing Technical Report (2509.19760)
π MM: VLM-Parsing: prithivMLmods/mm-vlm-parsing-68e33e52bfb9ae60b50602dc
β‘ Collections : prithivMLmods/multimodal-implementations-67c9982ea04b39f0608badb0
Other Pages:
β Multimodal VLMs - July'25 : prithivMLmods/multimodal-vlms-until-july25-688312e6b840e1e156f13027
β Multimodal VLMs - Aug'25 : prithivMLmods/multimodal-vlms-aug25-68a56aac39fe8084f3c168bd
β VL caption β < Sep 15 β25 : prithivMLmods/vl-caption-sep-15-25-68c7f6d737985c63c13e2391
.
.
.
To know more about it, visit the app page or the respective model page!!
reacted to anakin87's post with π₯ 11 months ago
Post
4749
Want to quickly try Gemma 3 270m? ππ¬
I made a simple Space to do that: anakin87/gemma-3-270m-it
β‘ Fast: Flash Attention, Zero GPU
βοΈ Configurable
I made a simple Space to do that: anakin87/gemma-3-270m-it
β‘ Fast: Flash Attention, Zero GPU
βοΈ Configurable
reacted to nroggendorff's post with π 11 months ago
Post
4716
No, I did not create those bots that just got banned today.
- 4 replies
reacted to albertvillanova's post with π 12 months ago
Post
4637
Latest smolagents release supports GPT-5: build agents that think, plan, and act.
β‘ Upgrade now and put GPT-5 to work!
β‘ Upgrade now and put GPT-5 to work!
- 1 reply
reacted to sergiopaniego's post with π₯ 12 months ago
Post
2204
OpenAI's open models are out! π
Try: https://www.gpt-oss.com/
Learn: https://huggingface.co/blog/welcome-openai-gpt-oss
Try: https://www.gpt-oss.com/
Learn: https://huggingface.co/blog/welcome-openai-gpt-oss
- 1 reply