Qwen/Qwen3.8-27B
Image-Text-to-Text • 28B • Updated • 91.9k • • 9.36k
Mex Ivanov
MexIvanov
AI & ML interests
NLP, Coding, Quantum Computing and more.
Recent Activity
liked a model about 18 hours ago
Qwen/Qwen3.8-27B liked a model about 2 months ago
zai-org/GLM-5.2 liked a model 2 months ago
unsloth/MiniMax-M3-GGUFOrganizations
None yet
liked a
model about 18 hours ago
liked a
model about 2 months ago
liked 2
models 2 months ago
reacted to HannesVonEssen's post with ❤️ 3 months ago
Post
290
📣 I made a visualizer for Hugging Face models: https://hfviewer.com
✨ Simply paste a Hugging Face URL to get an interactive visualization of the architecture!
🔗 The recent Qwen3.6-27B model as an example: https://hfviewer.com/Qwen/Qwen3.6-27B
Feel free to try it out and give me feedback on how it can be improved! ❤️
✨ Simply paste a Hugging Face URL to get an interactive visualization of the architecture!
🔗 The recent Qwen3.6-27B model as an example: https://hfviewer.com/Qwen/Qwen3.6-27B
Feel free to try it out and give me feedback on how it can be improved! ❤️
- 1 reply
upvoted a collection 3 months ago
liked a
model 4 months ago
liked a
dataset 4 months ago
reacted to fffiloni's post with 🤗 4 months ago
Post
3199
✨ PASD Magnify is back on Hugging Face Spaces
fffiloni/PASD
PASD isn’t recent, but still delivers strong results — worth restoring rather than replacing.
Getting it to run again wasn’t a simple dependency issue.
It relied on parts of diffusers that no longer exist, while moving to Gradio 6 forced a much newer HF stack — and I couldn’t modify the original source directly.
Recreating the old environment wasn’t practical.
So I patched the downloaded code at runtime before import and made it compatible with today’s stack.
That ended up being the only approach that held without forking or freezing everything to outdated versions.
If you’ve used it before (or are curious), feel free to give it another try.
fffiloni/PASD
PASD isn’t recent, but still delivers strong results — worth restoring rather than replacing.
Getting it to run again wasn’t a simple dependency issue.
It relied on parts of diffusers that no longer exist, while moving to Gradio 6 forced a much newer HF stack — and I couldn’t modify the original source directly.
Recreating the old environment wasn’t practical.
So I patched the downloaded code at runtime before import and made it compatible with today’s stack.
That ended up being the only approach that held without forking or freezing everything to outdated versions.
If you’ve used it before (or are curious), feel free to give it another try.
liked a
dataset 5 months ago
reacted to marksverdhei's post with 👍 6 months ago
Post
4638
Poll: Will 2026 be the year of subquadratic attention?
The transformer architecture is cursed by its computational complexity.
It is why you run out of tokens and have to compact. But some would argue that this is a feature not a bug and that this is also why these models are so good. We've been doing a lot of research on trying to make equally good models that are computationally cheaper, But so far, none of the approaches have stood the test of time. Or so it seems.
Please vote, don't be shy. Remember that the Dunning-Kruger effect is very real, so the person who knows less about transformers than you is going to vote. We want everyone's opinion, no matter confidence.
👍 if you think at least one frontier model* will have no O(n^2) attention by the end of 2026
🔥 If you disagree
* Frontier models - models that match / outperform the flagship claude, gemini or chatgpt at the time on multiple popular benchmarks
The transformer architecture is cursed by its computational complexity.
It is why you run out of tokens and have to compact. But some would argue that this is a feature not a bug and that this is also why these models are so good. We've been doing a lot of research on trying to make equally good models that are computationally cheaper, But so far, none of the approaches have stood the test of time. Or so it seems.
Please vote, don't be shy. Remember that the Dunning-Kruger effect is very real, so the person who knows less about transformers than you is going to vote. We want everyone's opinion, no matter confidence.
👍 if you think at least one frontier model* will have no O(n^2) attention by the end of 2026
🔥 If you disagree
* Frontier models - models that match / outperform the flagship claude, gemini or chatgpt at the time on multiple popular benchmarks
- 4 replies
liked 3
models 7 months ago
reacted to RakshitAralimatti's post with 🔥 8 months ago
Post
2464
I built something crazy you never saw before.
Please check - https://huggingface.co/blog/RakshitAralimatti/streaming-data-rag
A real-time Streaming Data to RAG system that listens to live radio, transcribes it on-the-fly, and lets you query across TIME.
Not just "what was discussed" – but "what happened in the last 10 minutes on channel 0?" or "at 9 AM, what was the breaking news?" This is RAG that understands temporal context.
Please check - https://huggingface.co/blog/RakshitAralimatti/streaming-data-rag
A real-time Streaming Data to RAG system that listens to live radio, transcribes it on-the-fly, and lets you query across TIME.
Not just "what was discussed" – but "what happened in the last 10 minutes on channel 0?" or "at 9 AM, what was the breaking news?" This is RAG that understands temporal context.
- 1 reply
reacted to samerzaher80's post with 👍 9 months ago
Post
1634
AetherMind_SRL: How I beat 7B models on MMLU with 184M params and a $300 GPU
I’m Sameer, a solo researcher from Iraq working on a single RTX 3050 8GB laptop.Today I’m releasing AetherMind_SRL – a 184M-parameter NLI model that was trained only on tasks (SNLI, MNLI, ANLI, and a small clinical Alzheimer’s dataset).
It was never fine-tuned or even shown a single MMLU question during training.Yet here are the zero-shot MMLU (57 subjects) results:Model
MMLU Zero-Shot
Training Data
AetherMind_SRL (me)
184M
36.05 %
Only NLI (SNLI/MNLI/ANLI + ADNI)
DeBERTa-v3-base
278M
~30.8 %
General pre-training
BERT-large
340M
27–30 %
General pre-training
LLaMA-1 7B
7B
34–35 %
Massive text corpus
LLaMA-2 7B
7B
~45 %
Bigger + better data
Yes – my 184M model beats every classic 300–400M model and the original 7-billion-parameter LLaMA-1, all while running at 300+ samples/sec on a $300 laptop GPU.How did this happen?I built a standardized self-improvement loop called AetherMind Self-Reflective Learning (SRL) v1.0:Train normally on NLI
Let the model predict on hard adversarial data (ANLI)
Log every mistake + low-confidence case
Build a balanced “SMART” buffer (60% errors + 40% correct anchors)
Fine-tune with tiny LR and error-weighted loss
Repeat until stable
That’s it. No external knowledge, no MMLU data, no cluster.
Just pure reasoning transfer from entailment/contradiction patterns → real-world knowledge.Try it yourself python
from transformers import pipeline
import torch
nli_pipeline = pipeline(
"text-classification",
model="samerzaher80/AetherMind_SRL",
device=0 if torch.cuda.is_available() else -1
)
# DEFINE YOUR TEST HERE
premise = "Patient shows progressive memory decline."
hypothesis = "Patient shows progressive memory decline."
input_text = f"{premise} [SEP] {hypothesis}"
result = nli_pipeline(input_text)[0]
print(f"Prediction: {result['label']}")
print(f"Confidence: {result['score']:
Model: samerzaher80/AetherMind_SRL
I’m Sameer, a solo researcher from Iraq working on a single RTX 3050 8GB laptop.Today I’m releasing AetherMind_SRL – a 184M-parameter NLI model that was trained only on tasks (SNLI, MNLI, ANLI, and a small clinical Alzheimer’s dataset).
It was never fine-tuned or even shown a single MMLU question during training.Yet here are the zero-shot MMLU (57 subjects) results:Model
MMLU Zero-Shot
Training Data
AetherMind_SRL (me)
184M
36.05 %
Only NLI (SNLI/MNLI/ANLI + ADNI)
DeBERTa-v3-base
278M
~30.8 %
General pre-training
BERT-large
340M
27–30 %
General pre-training
LLaMA-1 7B
7B
34–35 %
Massive text corpus
LLaMA-2 7B
7B
~45 %
Bigger + better data
Yes – my 184M model beats every classic 300–400M model and the original 7-billion-parameter LLaMA-1, all while running at 300+ samples/sec on a $300 laptop GPU.How did this happen?I built a standardized self-improvement loop called AetherMind Self-Reflective Learning (SRL) v1.0:Train normally on NLI
Let the model predict on hard adversarial data (ANLI)
Log every mistake + low-confidence case
Build a balanced “SMART” buffer (60% errors + 40% correct anchors)
Fine-tune with tiny LR and error-weighted loss
Repeat until stable
That’s it. No external knowledge, no MMLU data, no cluster.
Just pure reasoning transfer from entailment/contradiction patterns → real-world knowledge.Try it yourself python
from transformers import pipeline
import torch
nli_pipeline = pipeline(
"text-classification",
model="samerzaher80/AetherMind_SRL",
device=0 if torch.cuda.is_available() else -1
)
# DEFINE YOUR TEST HERE
premise = "Patient shows progressive memory decline."
hypothesis = "Patient shows progressive memory decline."
input_text = f"{premise} [SEP] {hypothesis}"
result = nli_pipeline(input_text)[0]
print(f"Prediction: {result['label']}")
print(f"Confidence: {result['score']:
Model: samerzaher80/AetherMind_SRL
liked 2
models 9 months ago
liked 2
models 10 months ago
