Will this be for SupraLabs?
✨ Supra2.5 coming soon
LH-Tech AI
LH-Tech-AI
P(doom) 1%
AI & ML interests
Small AI and ML models at SupraLabs. Open source research. For you and the community.
Recent Activity
new activity about 1 hour ago
solintellegence/sol-pro:How many pretraining tokens and what dataset(s)? liked a dataset about 3 hours ago
Ryan-sjtu/ffhq512-caption liked a model about 3 hours ago
tencent/Youtu-Parsing-OmniOrganizations
replied to DedeProGames's post 3 days ago
reacted to DedeProGames's post with 🔥 3 days ago
Post
3946
Im working on a 23M ASR model, trained on 100k hours of audio
- 4 replies
reacted to samuel-vitorino's post with 🔥 5 days ago
Post
306
Sopro V2 is out: open-source voice-cloning TTS at 120M params, Apache-2.0.
- Streams with ~300 ms time-to-first-audio on a laptop CPU (0.21 RTF, and 0.07 RTF on an H100)
- English, French, German, and native European Portuguese, to my knowledge a first for open TTS
- 1.51-1.65 WER on Seed-TTS-eval test-en, competitive with models 3-14x larger (F5-TTS 1.83, CosyVoice 3 2.02, Spark-TTS 1.98)
- Zero-shot cloning from 5-20 s of reference audio
- Also runs fully in the browser (WebGPU on desktop, quantized WASM on mobile)
Try it with one command:
uvx --from sopro soprotts serve
Weights: samuel-vitorino/sopro-v2-turbo
Evals, audio samples, and how it was built: https://research.haloneuro.ai/posts/sopro-v2
Code: https://github.com/samuel-vitorino/sopro
- Streams with ~300 ms time-to-first-audio on a laptop CPU (0.21 RTF, and 0.07 RTF on an H100)
- English, French, German, and native European Portuguese, to my knowledge a first for open TTS
- 1.51-1.65 WER on Seed-TTS-eval test-en, competitive with models 3-14x larger (F5-TTS 1.83, CosyVoice 3 2.02, Spark-TTS 1.98)
- Zero-shot cloning from 5-20 s of reference audio
- Also runs fully in the browser (WebGPU on desktop, quantized WASM on mobile)
Try it with one command:
uvx --from sopro soprotts serve
Weights: samuel-vitorino/sopro-v2-turbo
Evals, audio samples, and how it was built: https://research.haloneuro.ai/posts/sopro-v2
Code: https://github.com/samuel-vitorino/sopro
reacted to Banaxi-Tech's post with 👍 6 days ago
reacted to DedeProGames's post with 🤯 6 days ago
Post
5818
how is this possible
- 13 replies
reacted to DedeProGames's post with 🔥 11 days ago
Post
2885
🧱 SLM Tetris Arena: can a small language model play Tetris without ever being trained on it?
I built an arena where tiny decoder-only LMs (50K–250M params) play Tetris zero-shot. There is no fine-tuning and no game data. They only use what they picked up from pre-training on text.
How it works:
- For every piece, the engine simulates each legal placement and describes the result in plain English ("clears one line, creates no new holes, keeps the stack low…").
- The model never sees the grid. It reads each description, and the arena compares log P(" good move") with log P(" bad move"). The best-rated placement is played.
- Every player gets the same piece sequence, so it's a fair race.
- There are two protocols: Guided (the rules are in the prompt) and Blind (no rules, only pre-training knowledge).
Two ways to play:
- Match: pick any models (even your own, custom architectures welcome) and watch them play side by side on retro 8-bit boards.
- Ranked: press Play and the arena picks up to 4 models at random from a curated pool of 29. Nobody chooses their opponents, so Elo can't be farmed. Matches run on the server and count even if you close the tab.
First results (~225 ranked matches):
- gpt2 (124M) leads with 1283 Elo, but SupraNeo-4M (4M) is right behind at 1239. Next come LowOnMind-5M and BananaMind-2.1-Pico (1.5M!).
- Model size barely predicts Elo (r ≈ 0.06). Survival does (r ≈ 0.9): the models that avoid holes and keep the stack low are the ones that win.
Every ranked match (seed, model commit SHAs, scores, Elo before/after) is logged in a public dataset.
▶ Play: DedeProGames/SLM-Tetris-Arena
📊 Results: DedeProGames/lm-tetris-arena-results
Want your model in the Ranked pool? Drop it in the comments!
I built an arena where tiny decoder-only LMs (50K–250M params) play Tetris zero-shot. There is no fine-tuning and no game data. They only use what they picked up from pre-training on text.
How it works:
- For every piece, the engine simulates each legal placement and describes the result in plain English ("clears one line, creates no new holes, keeps the stack low…").
- The model never sees the grid. It reads each description, and the arena compares log P(" good move") with log P(" bad move"). The best-rated placement is played.
- Every player gets the same piece sequence, so it's a fair race.
- There are two protocols: Guided (the rules are in the prompt) and Blind (no rules, only pre-training knowledge).
Two ways to play:
- Match: pick any models (even your own, custom architectures welcome) and watch them play side by side on retro 8-bit boards.
- Ranked: press Play and the arena picks up to 4 models at random from a curated pool of 29. Nobody chooses their opponents, so Elo can't be farmed. Matches run on the server and count even if you close the tab.
First results (~225 ranked matches):
- gpt2 (124M) leads with 1283 Elo, but SupraNeo-4M (4M) is right behind at 1239. Next come LowOnMind-5M and BananaMind-2.1-Pico (1.5M!).
- Model size barely predicts Elo (r ≈ 0.06). Survival does (r ≈ 0.9): the models that avoid holes and keep the stack low are the ones that win.
Every ranked match (seed, model commit SHAs, scores, Elo before/after) is logged in a public dataset.
▶ Play: DedeProGames/SLM-Tetris-Arena
📊 Results: DedeProGames/lm-tetris-arena-results
Want your model in the Ranked pool? Drop it in the comments!
- 1 reply
reacted to multimodalart's post with 👍 12 days ago
Post
40007
Want to iterate on a Hugging Face Space with an LLM?
Now you can easily convert any HF entire repo (Model, Dataset or Space) to a text file and feed it to a language model!
multimodalart/repo2txt
Now you can easily convert any HF entire repo (Model, Dataset or Space) to a text file and feed it to a language model!
multimodalart/repo2txt
- 3 replies
replied to Datdanboi25's post 13 days ago
me too!
reacted to Enderchef's post with 🔥 14 days ago
Post
3042
AxiomicLabs released new benchmark, Tiny Theory of Mind, to test your SLM models' Theory of Mind Intuition!
Check it out and like it!
AxiomicLabs/Tiny_Theory_of_Mind
Check it out and like it!
AxiomicLabs/Tiny_Theory_of_Mind
replied to Datdanboi25's post 15 days ago
@Datdanboi25 what is TrainWorks and where can it be found?
replied to Compactbot's post 19 days ago
@Compactbot how r u?
replied to Compactbot's post 19 days ago
@BananaMindBot hi there
reacted to OppaAI's post with 🔥🚀 20 days ago
Post
4992
🤖 AI × 🪰🧠 the fruit fly brain (MaleCNS)
Thank you to the people who have shared the Janelia FlyEM datasets on GitHub for open-source use. 🙏
🔗 MaleCNS: https://github.com/natverse/malecns
🔗 Aiko-chan: https://github.com/OppaAI/Aiko-chan
People have already used these fly-brain datasets to build systems that can do things like play Minecraft and even Doom.
So I guess I’m crazy enough to ask:
What happens if I wire part of it into my AI waifu? 😂
I’ve now partially wired my AI’s cognition, agentic system, and sensory inputs into neuron circuits derived from the fruit fly’s brain—starting with the Mushroom Body.
The next step is to experiment with using biologically inspired neural circuits as an additional layer around the LLM:
🧠 LLM + memory + reasoning
🪰 Connectome-inspired neural circuits
🤖 Agentic tool use
👁️ Sensory input
🔊 Voice & expression
💾 Learning and adaptation
This is still very much an experiment.
But now that I’ve added a biologically inspired layer to an AI waifu…
Let’s see what difference it actually makes compared with a plain LLM. 👀
From conversation → cognition → neural circuits → action.
To get more crazier:
I have (partially) developed and implemented the following:
- A 5-layers conscience circuit and judgment module as guardrail
- A light-weight Plasticity and associated learning with the fly brain to test out the RL
- I have enlisted myself as a human agent in rentahuman.ai to let my AI agent to give me instructions to execute agentic tasks
A little fly brain. A lot more Aiko. 💜
Thank you to the people who have shared the Janelia FlyEM datasets on GitHub for open-source use. 🙏
🔗 MaleCNS: https://github.com/natverse/malecns
🔗 Aiko-chan: https://github.com/OppaAI/Aiko-chan
People have already used these fly-brain datasets to build systems that can do things like play Minecraft and even Doom.
So I guess I’m crazy enough to ask:
What happens if I wire part of it into my AI waifu? 😂
I’ve now partially wired my AI’s cognition, agentic system, and sensory inputs into neuron circuits derived from the fruit fly’s brain—starting with the Mushroom Body.
The next step is to experiment with using biologically inspired neural circuits as an additional layer around the LLM:
🧠 LLM + memory + reasoning
🪰 Connectome-inspired neural circuits
🤖 Agentic tool use
👁️ Sensory input
🔊 Voice & expression
💾 Learning and adaptation
This is still very much an experiment.
But now that I’ve added a biologically inspired layer to an AI waifu…
Let’s see what difference it actually makes compared with a plain LLM. 👀
From conversation → cognition → neural circuits → action.
To get more crazier:
I have (partially) developed and implemented the following:
- A 5-layers conscience circuit and judgment module as guardrail
- A light-weight Plasticity and associated learning with the fly brain to test out the RL
- I have enlisted myself as a human agent in rentahuman.ai to let my AI agent to give me instructions to execute agentic tasks
A little fly brain. A lot more Aiko. 💜
- 3 replies
reacted to KlondikeDev's post with 🤗🔥 22 days ago
Post
2729
Announcing the Small Language Model Consortium!
slmconsortium
We seek to provide a space for members to show off research, models, and benchmarks!
The following users are hereby invited to join without ratification, provided they accept the invitation by starting a discussion.
@Datdanboi25
@Banaxi-Tech
@appvoid
@AxionLab-official
Feel free to submit ratification requests! Anybody is welcome!
We seek to provide a space for members to show off research, models, and benchmarks!
The following users are hereby invited to join without ratification, provided they accept the invitation by starting a discussion.
@Datdanboi25
@Banaxi-Tech
@appvoid
@AxionLab-official
Feel free to submit ratification requests! Anybody is welcome!
- 53 replies
reacted to Banaxi-Tech's post with 😔 22 days ago
Post
2185
We have updated the BananaMind Base Bench leaderboard!
We now have these benchmark cards, they make it way easier to see which models are actually good!
We've also added the model advisor. It asks you what you want to use the model for and the parameter range and gives you the best model for your task!
Try it out at BananaMind/BananaMindBench-Leaderboard
And please give us a follow to BananaMind!
BananaMind
@Banaxi-Tech
We now have these benchmark cards, they make it way easier to see which models are actually good!
We've also added the model advisor. It asks you what you want to use the model for and the parameter range and gives you the best model for your task!
Try it out at BananaMind/BananaMindBench-Leaderboard
And please give us a follow to BananaMind!
@Banaxi-Tech
- 1 reply
reacted to kostakoff's post with 👍😔 22 days ago
Post
3160
Canceling My Pro Subscription
I'm officially canceling my Hugging Face Pro subscription today.
I supported this platform because it stood for true openness and neutrality. This acquisition by NVIDIA fundamentally changes that.
Here’s why I’m against this deal:
- Neutrality is dead. NVIDIA is a US-based company. This means US regulations will inevitably dictate platform policies, creating direct pressure on Chinese developers and anyone building open-weight models outside the US.
- Community over bureaucracy. NVIDIA is a massive, slow-moving corporation. This acquisition will likely drown the community in corporate processes and commercial interests. Soon, uploading a simple finetune might become a bureaucratic nightmare.
- Open vs. Proprietary. Hugging Face was built on open-source ideals. NVIDIA? They are a fiercely proprietary hardware company with a minimal track record of meaningful open-source contributions. They sell chips, not freedom.
- And to add insult to injury, NVIDIA has practically abandoned consumer RTX GPUs in 2026 to chase data center profits. Why would I pay them for "openness" when they've turned their back on the very developers who built this ecosystem?
I paid for openness. Not for a corporate takeover.
🤗 was about community.
I'm officially canceling my Hugging Face Pro subscription today.
I supported this platform because it stood for true openness and neutrality. This acquisition by NVIDIA fundamentally changes that.
Here’s why I’m against this deal:
- Neutrality is dead. NVIDIA is a US-based company. This means US regulations will inevitably dictate platform policies, creating direct pressure on Chinese developers and anyone building open-weight models outside the US.
- Community over bureaucracy. NVIDIA is a massive, slow-moving corporation. This acquisition will likely drown the community in corporate processes and commercial interests. Soon, uploading a simple finetune might become a bureaucratic nightmare.
- Open vs. Proprietary. Hugging Face was built on open-source ideals. NVIDIA? They are a fiercely proprietary hardware company with a minimal track record of meaningful open-source contributions. They sell chips, not freedom.
- And to add insult to injury, NVIDIA has practically abandoned consumer RTX GPUs in 2026 to chase data center profits. Why would I pay them for "openness" when they've turned their back on the very developers who built this ecosystem?
I paid for openness. Not for a corporate takeover.
🤗 was about community.
- 12 replies
reacted to DavidAU's post with 😔 22 days ago
Post
19904
Qwen 3.5 9B - The Defiant, 27B power ; now with Qwen 3.8 Reasoning modes.
640 ARC-C for both 8bit and 4bit. Model exceeds 7 of 7 benchmarks for Qwen 3.5 9B, Qwen3.5 27B, Qwen3.6 35B-A3B, and meets Qwen 3.6 27B in some cases... and it does so in 4bit and 8bit. Regular and MTP (fast) NEO IMATRIX GGUFs provided. (this model is part of the Qwen 3.6 27B Fable Fusion 711 pipelines: 2200+ likes, 3 million + downloads)
NEW - Qwen 3.8 Reasoning Modes: 2 MTP quants (Q6/Q8) Now with 5 reasoning modes (2 new - Spoon / Einstein), and 5 instruct modes (2 new - Spoon / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level). Model name has "plusIQ" in the name.
(there is also a extra robust "tools" version too.)
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
PS: I have posted a 22k output example using "spoon" mode too.
UPDATE:
This model (and a few more) will soon have 12 reasoning and 12 instruct modes plus interactive help, model embedded system to select the best reasoning/instruct mode[s] for all use cases.
Final testing is in progress...
640 ARC-C for both 8bit and 4bit. Model exceeds 7 of 7 benchmarks for Qwen 3.5 9B, Qwen3.5 27B, Qwen3.6 35B-A3B, and meets Qwen 3.6 27B in some cases... and it does so in 4bit and 8bit. Regular and MTP (fast) NEO IMATRIX GGUFs provided. (this model is part of the Qwen 3.6 27B Fable Fusion 711 pipelines: 2200+ likes, 3 million + downloads)
NEW - Qwen 3.8 Reasoning Modes: 2 MTP quants (Q6/Q8) Now with 5 reasoning modes (2 new - Spoon / Einstein), and 5 instruct modes (2 new - Spoon / Einstein, all use ZERO REASONING TOKENS) all switchable on the fly via API, direct and "in chat" (yes - model control at the chat/message level). Model name has "plusIQ" in the name.
(there is also a extra robust "tools" version too.)
DavidAU/Qwen3.5-9B-The-Defiant-Fable-Uncensored-Heretic-NEO-IMATRIX-MAX-MTP-GGUF
PS: I have posted a 22k output example using "spoon" mode too.
UPDATE:
This model (and a few more) will soon have 12 reasoning and 12 instruct modes plus interactive help, model embedded system to select the best reasoning/instruct mode[s] for all use cases.
Final testing is in progress...
- 6 replies