Post
1158
Tommorow we are releasing Supra2-Pro(100M params), our flagship, get ready!
(follow SupraLabs to get tuned in!)
SupraLabs
(follow SupraLabs to get tuned in!)
- 9 replies
๐๏ธ Building on HF
AxionLab
AxionLab-official
AI & ML interests
Owner of SupraLabs and iGPU Lover
Recent Activity
upvoted a collection about 5 hours ago
Our flagship CHAT models liked a model about 6 hours ago
User01110/AC-5M liked a model about 7 hours ago
SupraLabs/SupraBrain-50MOrganizations
reacted to their post with ๐ฅ about 16 hours ago
posted an update about 16 hours ago
reacted to LH-Tech-AI's post with โค๏ธ 1 day ago
Post
2277
Announcing The Supra2 Family And Supra2-100M
Today, we are announcing a brand-new series of SupraLabs models: Supra2
This series will feature various models, including such as:
- ๐ Supra2-Nano (0.4M) โ The smallest Supra2 model.
- ๐ค Supra2-Small (1.4M) โ The tiny model that runs everywhere.
- ๐ช Supra2-Medium (25M) โ Our medium class model in the Supra2 family. The powerful midsizer.
- ๐ฅ Supra2-Pro (100M): base, instruct, reasoning, code, math and more! โ The most capable model yet! A real allrounder for all your everyday tasks.
- ๐จ Supra2-IMG โ our generative text-to-image model
...and many more...
Current progress:
- Nano (0.4M) and Small (1.4M): in training; almost done. Baseline set.
- Medium (25M): coming soon...
- Pro (100M): in training; finishes in 66 hours - Monday, 3rd August 2026, 12:00AM
- IMG: coming soon...
You can support us with a like and follow if you want!
Don't miss our next release! Stay tuned...
Today, we are announcing a brand-new series of SupraLabs models: Supra2
This series will feature various models, including such as:
- ๐ Supra2-Nano (0.4M) โ The smallest Supra2 model.
- ๐ค Supra2-Small (1.4M) โ The tiny model that runs everywhere.
- ๐ช Supra2-Medium (25M) โ Our medium class model in the Supra2 family. The powerful midsizer.
- ๐ฅ Supra2-Pro (100M): base, instruct, reasoning, code, math and more! โ The most capable model yet! A real allrounder for all your everyday tasks.
- ๐จ Supra2-IMG โ our generative text-to-image model
...and many more...
Current progress:
- Nano (0.4M) and Small (1.4M): in training; almost done. Baseline set.
- Medium (25M): coming soon...
- Pro (100M): in training; finishes in 66 hours - Monday, 3rd August 2026, 12:00AM
- IMG: coming soon...
You can support us with a like and follow if you want!
Don't miss our next release! Stay tuned...
- 26 replies
reacted to their post with ๐ง ๐๐ฅ 1 day ago
Post
11041
THIS IS CRAZY! THE MODEL ON THE IMAGE(Supra-50M-Reasoning) answered correctly and its QUANTIZED IN 2BIT! THE RESPONSE IS CORRECT, IN A 15MB SIZE FILE!
- 15 replies
reacted to OppaAI's post with ๐ 1 day ago
Post
1051
After a month of interacting with my AI Waifu, I noticed a few issues in the system; so I decided to spend this week revisiting the systems implemented in Phase 1.0, 1.5 and 2.0, and try to make them to be more like production-grade as much as possible:
1) Memory Degradation - recalled memories are not as good as in the beginning, causing AI Waifu to be more chaotic as she hallucinates over contaminated memories like a bad vicious cycle.
So I transformed the original stateless sqlite-vec vector store to be a simple entity co-mention graph. And even make a studio to visualize the memories stored inside the vector db.
Just by looking at the graph, I saw a couple issues:
a) After 1.5 months of interactions, there should be only one month of pinned memory (in green) over 1.5 months of active memory (in purple). How come pinned memory is in majority over active ones?
I suppose the forgetting curve I had set too aggressive and memory half-life and shelf life too short, active memory got decayed way before monthly consolidation and got lost forever.
b) I saw she memorized me into 3 different entities: my username, my nickname and my Github user ID (leaked into pinned memory, presumbly during nightly dreaming process). 3B small param LLM has hard time to correlation 3 different entities into single person, I may have to harden into one.
2) RAM burst during voice input - for some reason the tensor calculation of SileroVAD of the voice input uses PyTorch, and that's the only place in the whole codebase using torch after removing it from TTS synthesization. By switching to SileroVAD-onnx integrated in the ASR sherpa-onnx, the RAM usage drops at least 0.5GB (after shaving off ~1GB from TTS) by completely remove PyTorch dependencies.
3) Introduced a better Wake Word system using Livekit-Wake word instead of using ASR to do the wake word activation to save computation. Optional features like Speak Verification, Barge-in sensitivity, etc, need to find the optimum settings.
1) Memory Degradation - recalled memories are not as good as in the beginning, causing AI Waifu to be more chaotic as she hallucinates over contaminated memories like a bad vicious cycle.
So I transformed the original stateless sqlite-vec vector store to be a simple entity co-mention graph. And even make a studio to visualize the memories stored inside the vector db.
Just by looking at the graph, I saw a couple issues:
a) After 1.5 months of interactions, there should be only one month of pinned memory (in green) over 1.5 months of active memory (in purple). How come pinned memory is in majority over active ones?
I suppose the forgetting curve I had set too aggressive and memory half-life and shelf life too short, active memory got decayed way before monthly consolidation and got lost forever.
b) I saw she memorized me into 3 different entities: my username, my nickname and my Github user ID (leaked into pinned memory, presumbly during nightly dreaming process). 3B small param LLM has hard time to correlation 3 different entities into single person, I may have to harden into one.
2) RAM burst during voice input - for some reason the tensor calculation of SileroVAD of the voice input uses PyTorch, and that's the only place in the whole codebase using torch after removing it from TTS synthesization. By switching to SileroVAD-onnx integrated in the ASR sherpa-onnx, the RAM usage drops at least 0.5GB (after shaving off ~1GB from TTS) by completely remove PyTorch dependencies.
3) Introduced a better Wake Word system using Livekit-Wake word instead of using ASR to do the wake word activation to save computation. Optional features like Speak Verification, Barge-in sensitivity, etc, need to find the optimum settings.
reacted to Enderchef's post with ๐ง ๐ค๐ฅ 2 days ago
Post
2334
I've left Glint Research.
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
AxiomicLabs
fromziro
SupraLabs
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
- 2 replies
reacted to Enderchef's post with โค๏ธ 3 days ago
Post
2334
I've left Glint Research.
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
AxiomicLabs
fromziro
SupraLabs
After a long time in Glint Research, an entire distributed training grid built free for them, and more, I've decided that I no longer want to be affiliated with Glint Research.
More updates will follow. Comments/questions are welcome.
While you're reading this, follow these orgs! Following takes just a few seconds, and can change someone's day.
- 2 replies
reacted to LH-Tech-AI's post with ๐ค๐ฅ 3 days ago
Post
2277
Announcing The Supra2 Family And Supra2-100M
Today, we are announcing a brand-new series of SupraLabs models: Supra2
This series will feature various models, including such as:
- ๐ Supra2-Nano (0.4M) โ The smallest Supra2 model.
- ๐ค Supra2-Small (1.4M) โ The tiny model that runs everywhere.
- ๐ช Supra2-Medium (25M) โ Our medium class model in the Supra2 family. The powerful midsizer.
- ๐ฅ Supra2-Pro (100M): base, instruct, reasoning, code, math and more! โ The most capable model yet! A real allrounder for all your everyday tasks.
- ๐จ Supra2-IMG โ our generative text-to-image model
...and many more...
Current progress:
- Nano (0.4M) and Small (1.4M): in training; almost done. Baseline set.
- Medium (25M): coming soon...
- Pro (100M): in training; finishes in 66 hours - Monday, 3rd August 2026, 12:00AM
- IMG: coming soon...
You can support us with a like and follow if you want!
Don't miss our next release! Stay tuned...
Today, we are announcing a brand-new series of SupraLabs models: Supra2
This series will feature various models, including such as:
- ๐ Supra2-Nano (0.4M) โ The smallest Supra2 model.
- ๐ค Supra2-Small (1.4M) โ The tiny model that runs everywhere.
- ๐ช Supra2-Medium (25M) โ Our medium class model in the Supra2 family. The powerful midsizer.
- ๐ฅ Supra2-Pro (100M): base, instruct, reasoning, code, math and more! โ The most capable model yet! A real allrounder for all your everyday tasks.
- ๐จ Supra2-IMG โ our generative text-to-image model
...and many more...
Current progress:
- Nano (0.4M) and Small (1.4M): in training; almost done. Baseline set.
- Medium (25M): coming soon...
- Pro (100M): in training; finishes in 66 hours - Monday, 3rd August 2026, 12:00AM
- IMG: coming soon...
You can support us with a like and follow if you want!
Don't miss our next release! Stay tuned...
- 26 replies
reacted to Banaxi-Tech's post with ๐ค๐ฅ 7 days ago
Post
7895
BananaMind 2 Pro is training!
The current checkpoint (ONLY 20% DONE) GETS #6 On the entire Open SLM Leaderboard.
We are going to release the first public preview on August 2-4 (estimated from speed)
Give us a follow to know when it releases!
The current checkpoint (ONLY 20% DONE) GETS #6 On the entire Open SLM Leaderboard.
We are going to release the first public preview on August 2-4 (estimated from speed)
Give us a follow to know when it releases!
- 4 replies
reacted to ProCreations's post with ๐คฏ๐๐ง ๐ 8 days ago
Post
2064
what should i do for 200 followers... hmmmm... top reply to this post (most emojis) wins, just not anything too crazy
- 11 replies