Post
2925
GLM 5 is insane, it ranks #4 Globally!
- 4 replies
Victor Mustar PRO
victor
AI & ML interests
Building the UX of this website
Recent Activity
liked
a Space
about 13 hours ago
Agnuxo/OpenCLAW-Agent
liked
a model
about 15 hours ago
Qwen/Qwen3.5-397B-A17B
liked
a model
about 19 hours ago
mlx-community/Nanbeige4.1-3B-8bit
Organizations
reacted to
Ujjwal-Tyagi's
post with ๐ฅ
1 day ago
reacted to
krisbailey's
post with ๐
1 day ago
Post
406
While doing various projects I kept running into situations where I wanted to be able to have representative samples of some of the current large SOTA datasets that were smaller so I didn't need to worry about slicing or anything else at runtime. So, I created sub datasets making sure to keep the same ratios of data sources. Each dataset card provides info for what's in it.
100M token datasets:
RedPajama v2 100M
Falcon RefinedWeb 100M
Cosmopedia 100M
1B token datasets:
Fineweb-edu 1B
RedPajama v1 1B
RedPajama v2 1B (use this one)
Cosmopedia 1B
10B token datasets:
RedPajama v1 10B
Cosmopedia 10B
Collection here:
https://huggingface.co/collections/krisbailey/bite-size-data
100M token datasets:
RedPajama v2 100M
Falcon RefinedWeb 100M
Cosmopedia 100M
1B token datasets:
Fineweb-edu 1B
RedPajama v1 1B
RedPajama v2 1B (use this one)
Cosmopedia 1B
10B token datasets:
RedPajama v1 10B
Cosmopedia 10B
Collection here:
https://huggingface.co/collections/krisbailey/bite-size-data
reacted to
danielhanchen's
post with ๐ฅ
1 day ago
Post
7266
You can now run MiniMax-2.5 locally! ๐
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.
Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF
At 230B parameters, MiniMax-2.5 is the strongest LLM under 700B params, delivering SOTA agentic coding & chat.
Run Dynamic 3/4-bit on a 128GB Mac for 20 tokens/s.
Guide: https://unsloth.ai/docs/models/minimax-2.5
GGUF: unsloth/MiniMax-M2.5-GGUF
- 1 reply
reacted to
kostakoff's
post with ๐
1 day ago
Post
3109
My home lab for AI models - llmlaba v1
After I began learning MLOps I realized that I needed some kind of home lab, there are a lot of GPUs that I need to learn how to set up and test.
So I spent some time to do a researching which platform I could buy or build.
My requirements ware:
- Limited budget
- Power supply 1 kW or higher
- Few PCIe slots to be able to install more than one gpu
- Zero maintenance cost, I don't want spend a lot of time or money to maintain lab hardware, except for the GPUs
I chose the Intel Mac Pro 7.1:
- Prices on eBay acceptable
- Excelent cooling
- 1.4 kW power supply
- 7 PCIe slots
- Zero maintenance: I don't need to do anything with the Mac Pro hardware; it just works
- Classic UEFI boot loader
It requires a bit of OS preparation:
1. Install Ubuntu 24.04 (it works with the general PC ISO image)
2. Set up T2 drivers
3. Install t2fanrd to manually manage fans (/etc/t2fand.conf) https://wiki.t2linux.org/guides/fan/
4. Fix PCIe BAR: add pci=realloc to GRUB_CMDLINE_LINUX_DEFAULT so the Linux kernel will properly initializes server GPUs without Graphics Output Protocol
5. Install NVIDIA GPU driver:
And it works!
I was able to run server-grade Nvidia Tesla P100 (required DIY air duct), and consumer Nvidia Titan X, Titan V, GTX 1080 cards on the old Mac Pro 7.1 - even three in parallel.
llmlaba
After I began learning MLOps I realized that I needed some kind of home lab, there are a lot of GPUs that I need to learn how to set up and test.
So I spent some time to do a researching which platform I could buy or build.
My requirements ware:
- Limited budget
- Power supply 1 kW or higher
- Few PCIe slots to be able to install more than one gpu
- Zero maintenance cost, I don't want spend a lot of time or money to maintain lab hardware, except for the GPUs
I chose the Intel Mac Pro 7.1:
- Prices on eBay acceptable
- Excelent cooling
- 1.4 kW power supply
- 7 PCIe slots
- Zero maintenance: I don't need to do anything with the Mac Pro hardware; it just works
- Classic UEFI boot loader
It requires a bit of OS preparation:
1. Install Ubuntu 24.04 (it works with the general PC ISO image)
2. Set up T2 drivers
sudo apt install -y dkms linux-headers-$(uname -r) applesmc-t2 apple-bce lm-sensors3. Install t2fanrd to manually manage fans (/etc/t2fand.conf) https://wiki.t2linux.org/guides/fan/
4. Fix PCIe BAR: add pci=realloc to GRUB_CMDLINE_LINUX_DEFAULT so the Linux kernel will properly initializes server GPUs without Graphics Output Protocol
5. Install NVIDIA GPU driver:
sudo apt install nvidia-driver-570And it works!
I was able to run server-grade Nvidia Tesla P100 (required DIY air duct), and consumer Nvidia Titan X, Titan V, GTX 1080 cards on the old Mac Pro 7.1 - even three in parallel.
- 3 replies
reacted to
AdinaY's
post with ๐ฅ
4 days ago
Post
2663
Game on ๐ฎ๐
While Seedance 2.0โs videos are all over the timeline, DeepSeek quietly pushed a new model update in its app.
GLM-5 from Z.ai adds more momentum.
Ming-flash-omni from Ant Group , MiniCPM-SALA from OpenBMB
, and the upcoming MiniMax M2.5 keep the heat on ๐ฅ
Spring Festival is around the corner,
no oneโs sleeping!
โจ More releases coming, stay tuned
https://huggingface.co/collections/zh-ai-community/2026-february-china-open-source-highlights
While Seedance 2.0โs videos are all over the timeline, DeepSeek quietly pushed a new model update in its app.
GLM-5 from Z.ai adds more momentum.
Ming-flash-omni from Ant Group , MiniCPM-SALA from OpenBMB
, and the upcoming MiniMax M2.5 keep the heat on ๐ฅ
Spring Festival is around the corner,
no oneโs sleeping!
โจ More releases coming, stay tuned
https://huggingface.co/collections/zh-ai-community/2026-february-china-open-source-highlights
reacted to
EricFillion's
post with ๐ฅ
4 days ago
Post
3636
Run open-source models with up to 120B parameters locally on your Mac!
https://youtu.be/Ql4PDjoxNXQ?si=3yHpz51uinUjgyNh
https://youtu.be/Ql4PDjoxNXQ?si=3yHpz51uinUjgyNh
- 2 replies
reacted to
danielhanchen's
post with ๐ฅ
6 days ago
Post
5060
We collaborated with Hugging Face to enable you to train MoE models 12ร faster with 35% less VRAM via our new Triton kernels (no accuracy loss). ๐ค
Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
Train gpt-oss locally on 12.8GB VRAM with our free notebooks: https://unsloth.ai/docs/new/faster-moe
- 1 reply
reacted to
alexnasa's
post with ๐
6 days ago
Post
2255
Now with extra functionality at the same LTX-2 HF Space, you can now add also your last frame along side your first frame to guide the generated videos by choosing our frame interpolation mode...
Try it out: alexnasa/ltx-2-TURBO
Try it out: alexnasa/ltx-2-TURBO
reacted to
AdinaY's
post with ๐ฅ
12 days ago
Post
1313
โจ Chinaโs open source AI ecosystem has entered a new phase
https://huggingface.co/blog/huggingface/one-year-since-the-deepseek-moment-blog-3
One year after the โDeepSeek Moment,โ open source has become the default. Models, research, infrastructure, and deployment are increasingly shared to support large-scale, system-level integration.
This final blog examines how leading Chinese AI organizations are evolving ,and what this implies for the future of open source.
https://huggingface.co/blog/huggingface/one-year-since-the-deepseek-moment-blog-3
One year after the โDeepSeek Moment,โ open source has become the default. Models, research, infrastructure, and deployment are increasingly shared to support large-scale, system-level integration.
This final blog examines how leading Chinese AI organizations are evolving ,and what this implies for the future of open source.
reacted to
alibidaran's
post with ๐ฅ
12 days ago
Post
2932
Iโm excited to share PlaiTO, a reasoning-focused language model built on LLaMA 3.1 (8B) and optimized for humanities and social sciences.
PlaiTO is designed to go beyond surface-level text generation, emphasizing structured reasoning, conceptual clarity, and analytical depthโespecially in domains centered on human behavior and social systems.
๐ฏ Focus Areas
Psychology
Management & Organizational Studies
Sociology
๐ MMLU Benchmark Results (100 samples per domain)
Professional Psychology: 76%
Management: 74%
Sociology: 75%
These results highlight PlaiTOโs strong performance in abstract, theory-heavy, and reasoning-driven tasks.
๐ก Why PlaiTO?
Strong analytical and reasoning capabilities
Better handling of complex human-centered problems
Suitable for academic, educational, and research use cases
Balanced performance across multiple humanities disciplines
PlaiTO is ideal for conceptual analysis, case reasoning, academic discussion, and decision-support scenariosโwhile still requiring human oversight for high-stakes applications.
๐ Built on LLaMA 3.1, compliant with its licensing terms.
alibidaran/Platio_merged_model
PlaiTO is designed to go beyond surface-level text generation, emphasizing structured reasoning, conceptual clarity, and analytical depthโespecially in domains centered on human behavior and social systems.
๐ฏ Focus Areas
Psychology
Management & Organizational Studies
Sociology
๐ MMLU Benchmark Results (100 samples per domain)
Professional Psychology: 76%
Management: 74%
Sociology: 75%
These results highlight PlaiTOโs strong performance in abstract, theory-heavy, and reasoning-driven tasks.
๐ก Why PlaiTO?
Strong analytical and reasoning capabilities
Better handling of complex human-centered problems
Suitable for academic, educational, and research use cases
Balanced performance across multiple humanities disciplines
PlaiTO is ideal for conceptual analysis, case reasoning, academic discussion, and decision-support scenariosโwhile still requiring human oversight for high-stakes applications.
๐ Built on LLaMA 3.1, compliant with its licensing terms.
alibidaran/Platio_merged_model
reacted to
danielhanchen's
post with ๐๐คฏ๐ฅ
12 days ago
Post
3721
Qwen releases Qwen3-Coder-Next! ๐ Run the locally on 46GB RAM or less.
Thhe model excels at agentic coding & local use. With 256K context, it delivers similar performance to models with 10-20ร more active parameters.
GGUF: unsloth/Qwen3-Coder-Next-GGUF
Guide: https://unsloth.ai/docs/models/qwen3-coder-next
Thhe model excels at agentic coding & local use. With 256K context, it delivers similar performance to models with 10-20ร more active parameters.
GGUF: unsloth/Qwen3-Coder-Next-GGUF
Guide: https://unsloth.ai/docs/models/qwen3-coder-next
-
- 9 replies
reacted to
prithivMLmods's
post with ๐ฅ
12 days ago
Post
2139
Introducing the Qwen-Image-Edit-3D-Lighting-Control app, featuring 8ร horizontal and 3ร elevational lighting positions for precise 3D lighting control. It enables studio-level lighting using fast Qwen Image Edit fast inference, paired with Multi-Angle-Lighting adapters. ๐ฆ
๐ฅ Space: prithivMLmods/Qwen-Image-Edit-3D-Lighting-Control
โ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-3D-Lighting-Control
๐ฅ Space: prithivMLmods/Qwen-Image-Edit-3D-Lighting-Control
โ Collection: https://huggingface.co/collections/prithivMLmods/image-generation-apps-collection
๐ GitHub: https://github.com/PRITHIVSAKTHIUR/Qwen-Image-Edit-3D-Lighting-Control
posted
an
update
19 days ago
Post
653
Interesting article: use Claude Code to help open models write CUDA kernels (for eg) by turning CC traces into Skills. They made a library out of it ๐
https://huggingface.co/blog/upskill
https://huggingface.co/blog/upskill
reacted to
danielhanchen's
post with ๐
20 days ago
Post
3409
You can now run Kimi K2.5 locally! ๐ฅ
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
We shrank the 1T model to 240GB (-60%) via Dynamic 1-bit.
Get >40 tok/s on 242GB or 622GB VRAM/RAM for near full precision.
GGUF: unsloth/Kimi-K2.5-GGUF
Guide: https://unsloth.ai/docs/models/kimi-k2.5
-
- 7 replies
reacted to
tegridydev's
post with โค๏ธ
20 days ago
Post
1904
Introducing OpenMALx
openmalx
Repository for Infosec and Machine Learning Resources
OpenMALx is an organization focused on the development of datasets and models for security analysis. The project objective is to provide structured data for training and evaluating large language models in a security context.
---
Technical Focus
**Dataset Formatting:** Processing raw security tool logs into instruction/response pairs for model training.
**Local Execution:** Optimizing models for local hardware to ensure data remains on-premises.
**Response Logic:** Developing structured formats for explaining security vulnerabilities and remediation steps.
Active Projects
**infosec-tool-output:** A dataset mapping static and dynamic analysis tool outputs to technical summaries.
openmalx/infosec-tool-output
**open-malsec:** A collection of text-based security threats, including phishing and social engineering samples, for classification tasks.
openmalx/open-malsec
Repository for Infosec and Machine Learning Resources
OpenMALx is an organization focused on the development of datasets and models for security analysis. The project objective is to provide structured data for training and evaluating large language models in a security context.
---
Technical Focus
**Dataset Formatting:** Processing raw security tool logs into instruction/response pairs for model training.
**Local Execution:** Optimizing models for local hardware to ensure data remains on-premises.
**Response Logic:** Developing structured formats for explaining security vulnerabilities and remediation steps.
Active Projects
**infosec-tool-output:** A dataset mapping static and dynamic analysis tool outputs to technical summaries.
openmalx/infosec-tool-output
**open-malsec:** A collection of text-based security threats, including phishing and social engineering samples, for classification tasks.
openmalx/open-malsec
will it be open sourced?
Cool! can I use from my CLI or must do some python scripting?
reacted to
danieldk's
post with ๐ฅ
21 days ago
Post
2717
kernels 0.12 is out! ๐
Changes:
* Support for kernel version branches to gracefully roll out kernel API changes.
* Support for PyTorch 2.10.
* kernel-builder is now merged into the kernels repo.
* Initial support for standardized kernel benchmarks.
https://github.com/huggingface/kernels/releases/tag/v0.12.0
Changes:
* Support for kernel version branches to gracefully roll out kernel API changes.
* Support for PyTorch 2.10.
* kernel-builder is now merged into the kernels repo.
* Initial support for standardized kernel benchmarks.
https://github.com/huggingface/kernels/releases/tag/v0.12.0