Post
68
NEW CLAUDE HAIKU MODEL COMING
FINALLY AFTER A YEAR
ANTHROPIC ANNOUNCED HAIKU 5.5
FINALLY AFTER A YEAR
ANTHROPIC ANNOUNCED HAIKU 5.5
🟥 I ❤️ İvmeLabs
Eren Ekşi
ereniko
AI & ML interests
Optimizing training like crazy. And seals, they're not AI-related, but whatever.
Recent Activity
updated a Space about 9 hours ago
bench-labs/README liked a model 1 day ago
Compactbot/sealglazer-1.9m new activity 2 days ago
ereniko/SmolLLM2-135M-Code:testingOrganizations
posted an update 2 days ago
This comment has been hidden
replied to NILKNARFGonzo's post 4 days ago
Open MFA with a TOTP app that should solve it.
reacted to KlondikeDev's post with 😔 5 days ago
Post
195
Important Boris-2 news:
Boris-2 is 30B out of 200B tokens in, and it is severely behind its competitors in training.
We have determined the bug to be a configuration error. Boris-2 has been in training for ~1 week, and was projected to finish on November 3rd, 2026.
We are unfortunately going to restart training, with proper configuration.
The new projected finish date is ~15-18th of November.
We apologize for the delay.
Boris-2 is 30B out of 200B tokens in, and it is severely behind its competitors in training.
We have determined the bug to be a configuration error. Boris-2 has been in training for ~1 week, and was projected to finish on November 3rd, 2026.
We are unfortunately going to restart training, with proper configuration.
The new projected finish date is ~15-18th of November.
We apologize for the delay.
- 17 replies
reacted to GoktugD's post with ❤️ 30 days ago
Post
2004
🇹🇷 Introducing T3 Gemstone — Edge AI & Cybersecurity Models from Türkiye
We've been building an open AI ecosystem focused on practical models that can run closer to the edge — not only in large datacenters.
Today, I'm introducing T3 Gemstone, a growing family of compact AI models built around edge inference, cybersecurity and computer vision.
💎 T3 Gemstone currently includes:
* NanoSOC Gemstone 2B — GGUF
* NanoSOC Gemstone 4B — GGUF
* Gemstone Person/Object Detector Nano
* Edge-focused AI experiments and deployments
The goal is simple:
Build smaller, practical and open AI systems that can actually run on constrained hardware.
This is part of a much larger open-source effort we're building from Türkiye across LLMs, cybersecurity, computer vision, retrieval, speech and edge AI.
There is much more coming.
🤗 Explore my models, datasets and demos:
@GoktugD
🛡️ NanoSOC:
Werea-co/Werea-NanoSOC-8B
Feedback, benchmarks, collaborations and contributions are very welcome.
If you're interested inopen-source AI, Turkish AI research, edge AI or cybersecurity models, follow the journey.
We're just getting started. 🇹🇷
#AI #OpenSource #HuggingFace #LLM #EdgeAI #Cybersecurity #ComputerVision #TurkishAI #MachineLearning
We've been building an open AI ecosystem focused on practical models that can run closer to the edge — not only in large datacenters.
Today, I'm introducing T3 Gemstone, a growing family of compact AI models built around edge inference, cybersecurity and computer vision.
💎 T3 Gemstone currently includes:
* NanoSOC Gemstone 2B — GGUF
* NanoSOC Gemstone 4B — GGUF
* Gemstone Person/Object Detector Nano
* Edge-focused AI experiments and deployments
The goal is simple:
Build smaller, practical and open AI systems that can actually run on constrained hardware.
This is part of a much larger open-source effort we're building from Türkiye across LLMs, cybersecurity, computer vision, retrieval, speech and edge AI.
There is much more coming.
🤗 Explore my models, datasets and demos:
@GoktugD
🛡️ NanoSOC:
Werea-co/Werea-NanoSOC-8B
Feedback, benchmarks, collaborations and contributions are very welcome.
If you're interested inopen-source AI, Turkish AI research, edge AI or cybersecurity models, follow the journey.
We're just getting started. 🇹🇷
#AI #OpenSource #HuggingFace #LLM #EdgeAI #Cybersecurity #ComputerVision #TurkishAI #MachineLearning
replied to Banaxi-Tech's post about 1 month ago
Absolutely not you can check my own models Ivme-Conversate-S-v1-Base and S-v2-Instruct if you want I hate to do unrelated mentioning but
They literally do what you say
Low training tokens, different architecture (for v1), high quality data and it flopped so bad I didn't put v2 to leaderboards.
Second you said SmolLM2 uses curated data
Well
I guess what do we use
Take a wild guess it's FineWeb-Edu!
Why?
BECAUSE IT'S HUGGINGFACE
THAT'S THE POINT OF HUGGINGFACE
Also you said things about water usage I can tell you BananaMind's model is definitely more efficient in the amount of compute spent on what hardware.
reacted to Enderchef's post with ❤️ about 2 months ago
Post
3319
GPT-X2.5-135M is finally released! 🚀
The new flagship from Axiomic Labs takes 3rd on the open SLM leaderboard trailing only the SmolLMs, check it out and follow us:
AxiomicLabs/GPT-X2.5-135M
The new flagship from Axiomic Labs takes 3rd on the open SLM leaderboard trailing only the SmolLMs, check it out and follow us:
AxiomicLabs/GPT-X2.5-135M
- 2 replies
reacted to FlameF0X's post with ❤️ about 2 months ago
Post
327
Hello, people of Hugging Face!
I recently released FlameF0X/TinyMoE-100m-2x8-retrained, a small Mixture of Experts language model trained on the Smollm-Corpus. Built on top of the Mixtral architecture, it’s fully compatible with 🤗 Transformers right out of the box!
The model can produce somewhat coherent text on its own, and for some reason, it generates even more coherent responses when given a ChatLM template.
I’m excited to see what you all come up with, and feel free to fine-tune it if you’d like. In the meantime, I’ll be working on developing the chat-trained version.
Demo: FlameF0X/TinyMoE-Playground
Collection: https://huggingface.co/collections/FlameF0X/tinymoe
I recently released FlameF0X/TinyMoE-100m-2x8-retrained, a small Mixture of Experts language model trained on the Smollm-Corpus. Built on top of the Mixtral architecture, it’s fully compatible with 🤗 Transformers right out of the box!
The model can produce somewhat coherent text on its own, and for some reason, it generates even more coherent responses when given a ChatLM template.
I’m excited to see what you all come up with, and feel free to fine-tune it if you’d like. In the meantime, I’ll be working on developing the chat-trained version.
Demo: FlameF0X/TinyMoE-Playground
Collection: https://huggingface.co/collections/FlameF0X/tinymoe
reacted to HannesVonEssen's post with 🚀🔥🤗❤️ about 2 months ago
Post
2335
🏅 HF Viewer podium
Our top most active users:
🥇#1 @Quazim0t0
🥈#2 @IvmeLabs
🥉#3 @GODELEV
If you are an HF creator and want to try entering the podium, feel free to visit the embed page to add your graph!
https://hfviewer.com/model-card-embed
Our top most active users:
🥇#1 @Quazim0t0
🥈#2 @IvmeLabs
🥉#3 @GODELEV
If you are an HF creator and want to try entering the podium, feel free to visit the embed page to add your graph!
https://hfviewer.com/model-card-embed
- 2 replies
reacted to AxionLab-official's post with ❤️😔 3 months ago
Post
5172
⚠️ Community Notice
We would like to clarify that SupraLabs has no affiliation, partnership, or connection whatsoever with "SupraLarps" or its members.
Please avoid interacting with their organization, repositories, or Spaces under the assumption that they are associated with us.
We are currently aware of the situation and have already contacted the appropriate channels to address it.
Thank you to everyone who continues to support SupraLabs. ❤️
We would like to clarify that SupraLabs has no affiliation, partnership, or connection whatsoever with "SupraLarps" or its members.
Please avoid interacting with their organization, repositories, or Spaces under the assumption that they are associated with us.
We are currently aware of the situation and have already contacted the appropriate channels to address it.
Thank you to everyone who continues to support SupraLabs. ❤️
- 12 replies
replied to AxionLab-official's post 3 months ago
Why is Supralabs getting a lot of drama every day recently? There are trolls everywhere its sad looking at it.
replied to AxionLab-official's post 4 months ago
I mean, like, we are talking about a 50M model here. That thing, already in full precision, can barely do basic math. On 2 bits, even a single question being right is impressive.
posted an update 4 months ago
Post
397
Something concerning is happening with Nvidia's GPU pricing and benchmark transparency.
Look at how other hardware generations work: a new iPhone costs roughly what the previous one did. Same with Samsung Galaxy phones, same with AMD Ryzen CPUs. Price increases are modest and the specs are straightforward to compare. Nvidia has broken from this pattern. Each new generation costs meaningfully more than the last, while the benchmarks get harder to interpret, not easier.
Look at what's happening with the numbers. BF16 and FP16 performance figures, the ones most relevant for real workloads, are increasingly buried or absent. Sparsity is baked into headline numbers without always being clearly flagged. The B200 is being benchmarked as an NVLink pair rather than a single card in some comparisons. Each of these is defensible in isolation, but together they make it genuinely hard to do apples-to-apples comparisons across generations.
The inference vs training tension is worth flagging too. Lower precision formats are good for inference but introduce real tradeoffs for training. As Nvidia pushes further into inference optimization, NVFP4 being the latest example, it raises a fair question about where training workloads go. NVFP4 training exists, but documentation and real-world results are thin enough that most teams aren't seriously evaluating it yet.
The "ROCm is immature" narrative is also getting a bit stale. I've personally run workloads on the MI300X and honestly it felt smoother than I expected, even compared to CUDA in some cases. And the price to performance ratio isn't even close. AMD isn't a consolation prize anymore.
At some point, labs and enterprises doing the actual buying will have enough alternatives like AMD MI300X, custom silicon, and inference-optimized ASICs to push back. Nvidia is standing on thin ice, and a few more steps like this might be enough to crack it.
Look at how other hardware generations work: a new iPhone costs roughly what the previous one did. Same with Samsung Galaxy phones, same with AMD Ryzen CPUs. Price increases are modest and the specs are straightforward to compare. Nvidia has broken from this pattern. Each new generation costs meaningfully more than the last, while the benchmarks get harder to interpret, not easier.
Look at what's happening with the numbers. BF16 and FP16 performance figures, the ones most relevant for real workloads, are increasingly buried or absent. Sparsity is baked into headline numbers without always being clearly flagged. The B200 is being benchmarked as an NVLink pair rather than a single card in some comparisons. Each of these is defensible in isolation, but together they make it genuinely hard to do apples-to-apples comparisons across generations.
The inference vs training tension is worth flagging too. Lower precision formats are good for inference but introduce real tradeoffs for training. As Nvidia pushes further into inference optimization, NVFP4 being the latest example, it raises a fair question about where training workloads go. NVFP4 training exists, but documentation and real-world results are thin enough that most teams aren't seriously evaluating it yet.
The "ROCm is immature" narrative is also getting a bit stale. I've personally run workloads on the MI300X and honestly it felt smoother than I expected, even compared to CUDA in some cases. And the price to performance ratio isn't even close. AMD isn't a consolation prize anymore.
At some point, labs and enterprises doing the actual buying will have enough alternatives like AMD MI300X, custom silicon, and inference-optimized ASICs to push back. Nvidia is standing on thin ice, and a few more steps like this might be enough to crack it.
posted an update 5 months ago
Post
522
I don't know why, but lately there's been a growing problem on HuggingFace: the platform is filled to the brim with datasets of reasoning traces from large AI models. I feel like someone should address this, but the dataset tab is just full of reasoning and output traces from models like Claude Opus and the model tab is full of fine-tunes trained on these.
What scares me most are the legal consequences of this, and the possibility that all models will start converging on the same tone because everyone is just fine-tuning on everyone else.
What scares me most are the legal consequences of this, and the possibility that all models will start converging on the same tone because everyone is just fine-tuning on everyone else.
- 1 reply
Opus 4.6 released
But idk this thing didnt really looked like a magic.
Though Sonnet 5 could also drop i dunno.