Post
3678
We got gpt6 before gta6
- 15 replies
ZeroGPU Explorers
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Post
109
Any thoughts on Nvidia acquiring this website?
I don't know what to feel about it. But would be great if huggingface gets something similar to Kaggle with free GPU hours (or even days) for training.
I don't know what to feel about it. But would be great if huggingface gets something similar to Kaggle with free GPU hours (or even days) for training.
- 3 replies
ZeroGPU clone fails during tensor packing with Errno 28 โ 82.1 GB pack target
1
#185 opened 6 days ago
by 
Thananon
Post
3292
Love how the small lm community is getting identity over time:
- Channel-Mixing
- XSA
- Three-tower
- Digit aware
- Loops
No one is doing the same! That's so cool.
- Channel-Mixing
- XSA
- Three-tower
- Digit aware
- Loops
No one is doing the same! That's so cool.
- 36 replies
Post
2637
Nobody knows what is doing, when you train a model, you are experimenting to advance the frontier, so keep failing ๐ซต
- 17 replies
Post
2597
I hope that after this OpenAI disaster on Plus users, more people start realizing why Open Weights were always the only way.
- 5 replies
Post
1002
Byte-level state-space models. That sounded pretty scary for a scientist decades ago. Now we have:
1. Knowledge that deeper layers train smoothly.
2. Knowledge that Transformers work but is quadratic on sequence length.
3. Knowledge that SSMs work even better. Numerically unstable sometimes.
4. Speculative-decoding.
5. Open high-quality data.
6. Knowledge that KD works.
It slowly feels like is no longer a bad idea.
1. Knowledge that deeper layers train smoothly.
2. Knowledge that Transformers work but is quadratic on sequence length.
3. Knowledge that SSMs work even better. Numerically unstable sometimes.
4. Speculative-decoding.
5. Open high-quality data.
6. Knowledge that KD works.
It slowly feels like is no longer a bad idea.
- 3 replies
Post
166
It's 2026 and there are no instantaneous/fast vision language models for cpus yet. That's another free idea.
- 6 replies
Post
143
CaraArchive highlights a broader reality of putting data online: once something is publicly accessible, it becomes extremely difficult to guarantee that it will remain under your control.
If there is information or artwork that you absolutely do not want copied, archived, scraped, downloaded, or used by others, the safest option is still not to publish it publicly in the first place. That may sound obvious, but the internet was fundamentally designed to move and reproduce information, and there are countless ways to retrieve publicly accessible images:from ordinary browser tools and web scraping to automated or agentic systems.
That does not mean artists should simply accept every possible use of their work. Artists deserve meaningful control, attribution, compensation, and reasonable ways to express how their work may be used. But treating the technology and peopple using it itself as the enemy is unlikely to solve the underlying problem.
There probably isn't a technical solution that can make a publicly visible image simultaneously viewable by everyone and impossible to copy. The realistic goal should therefore be to create better norms, incentives, licensing systems, and tools around how that content is used.
Like, we can imagine a future where every artist gets his/her own credentials and some kind of fingerprint done just like blockchain works. But that requires substantial cooperation among organizations, companies and individuals.
Technology and art are not inherently opposing sides though.
If there is information or artwork that you absolutely do not want copied, archived, scraped, downloaded, or used by others, the safest option is still not to publish it publicly in the first place. That may sound obvious, but the internet was fundamentally designed to move and reproduce information, and there are countless ways to retrieve publicly accessible images:from ordinary browser tools and web scraping to automated or agentic systems.
That does not mean artists should simply accept every possible use of their work. Artists deserve meaningful control, attribution, compensation, and reasonable ways to express how their work may be used. But treating the technology and peopple using it itself as the enemy is unlikely to solve the underlying problem.
There probably isn't a technical solution that can make a publicly visible image simultaneously viewable by everyone and impossible to copy. The realistic goal should therefore be to create better norms, incentives, licensing systems, and tools around how that content is used.
Like, we can imagine a future where every artist gets his/her own credentials and some kind of fingerprint done just like blockchain works. But that requires substantial cooperation among organizations, companies and individuals.
Technology and art are not inherently opposing sides though.
All ZeroGPU Spaces stuck on "Starting" with clean logs โ CPU and paid GPU unaffected
๐ 2
3
#183 opened 25 days ago
by 
luna0805
Post
175
If you lack ideas for a cool model, here's one.
Train a model from scratch on wikipedia with one twist: the tokenizer changes the actual token ids used on every sample fed. If somehow still learns English, you have made an astonishing discovery.
You would have answered the question: Can a model learn human languages from structure alone?
Train a model from scratch on wikipedia with one twist: the tokenizer changes the actual token ids used on every sample fed. If somehow still learns English, you have made an astonishing discovery.
You would have answered the question: Can a model learn human languages from structure alone?
- 2 replies
Post
1968
Random corporate secret of tonight:
Try overfitting a tiny model on billions of high-quality datapoints: you can't. You can do 100 epochs and see the model still improving.
You're welcome.
Try overfitting a tiny model on billions of high-quality datapoints: you can't. You can do 100 epochs and see the model still improving.
You're welcome.
- 1 reply
Post
864
- GLM 5.2
- Flux 3
- New Qwen model
- New small model leaderboards
- Lots of people finetuning smol models.
- Some even under 12 year olds clauders are here (was not on my bingo card this year)
- ChatGPT's Sol became a lot faster this week
- LFM2.5 2.6b
- Kimi K3 (though only a few will run it)
- New Ling 3.0 Tiny
- New video model that is making south park videos?
- Deepseek v4 flash being more honest than bigger models
- The new model from meta
Everything Everywhere All At Once
- Flux 3
- New Qwen model
- New small model leaderboards
- Lots of people finetuning smol models.
- Some even under 12 year olds clauders are here (was not on my bingo card this year)
- ChatGPT's Sol became a lot faster this week
- LFM2.5 2.6b
- Kimi K3 (though only a few will run it)
- New Ling 3.0 Tiny
- New video model that is making south park videos?
- Deepseek v4 flash being more honest than bigger models
- The new model from meta
Everything Everywhere All At Once
- 1 reply
Ikerย
submitted a
paper to Daily Papers 30 days ago
BramVanroyย
posted an update 30 days ago
Post
2710
**I benchmarked HF buckets against https access for Common Crawl.**
Took me a while to get round to do this but I benchmarked access to Common Crawl via https vs hf buckets. Both experiments were run at night in Europe. I do not think other hardware problems were impacting the speeds since CPU processing time of the non-download pipeline components were highly similar (within 2% identical) and below only the WarcReader speeds of datatrove are used.
Experiment: selected 5 disjoint samples of 64 files each (randomly from the latest crawl; 20,499 docs/file). Those five batches were then processed by 32 single-core tasks with 4GB/core (five batches to calculate CIs). Paired experiment between using https and hf bucket.
- https: 40.0 [39.3-40.6] (seconds per WARC file)
- hf bucket: 172.0 [122.7-221.2]
That is a difference of about 4x in streaming speed. You'll see that https is also more stable (smaller CI).
I also ran raw throughput tests to the endpoints to measure rate limiting (64MiB transfer at 8/32/128/256 concurrent readers) and rate limiting seems not an issue for either: at any of those parallel reader numbers, their respective speeds stay about the same.
Note that, given CC scale, this is still a small test. Rate limiting may become more obvious when processing a full crawl. I do not know whether the https endpoint vs HF bucket will shut you out earlier with which limits.
Took me a while to get round to do this but I benchmarked access to Common Crawl via https vs hf buckets. Both experiments were run at night in Europe. I do not think other hardware problems were impacting the speeds since CPU processing time of the non-download pipeline components were highly similar (within 2% identical) and below only the WarcReader speeds of datatrove are used.
Experiment: selected 5 disjoint samples of 64 files each (randomly from the latest crawl; 20,499 docs/file). Those five batches were then processed by 32 single-core tasks with 4GB/core (five batches to calculate CIs). Paired experiment between using https and hf bucket.
- https: 40.0 [39.3-40.6] (seconds per WARC file)
- hf bucket: 172.0 [122.7-221.2]
That is a difference of about 4x in streaming speed. You'll see that https is also more stable (smaller CI).
I also ran raw throughput tests to the endpoints to measure rate limiting (64MiB transfer at 8/32/128/256 concurrent readers) and rate limiting seems not an issue for either: at any of those parallel reader numbers, their respective speeds stay about the same.
Note that, given CC scale, this is still a small test. Rate limiting may become more obvious when processing a full crawl. I do not know whether the https endpoint vs HF bucket will shut you out earlier with which limits.
Post
2389
I don't know if it was us or one of you guys or maybe all of us at once but lately we have seen a finetuning/pretraining explosion of models below 200m params and we can't be more happy about it keep coming tinkerers all of this is possible because of you!
- 8 replies
Post
2909
If you want small models to be great again you should give a follow to people like @Banaxi-Tech or @Datdanboi25
These guys are rocking it with small models lately.
(They are not paying me to say that)
These guys are rocking it with small models lately.
(They are not paying me to say that)
- 22 replies
Ikerย
authored 3
papers about 1 month ago
Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL Loss
Paper โข 2608.03796 โข Published โข 17
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Paper โข 2512.16602 โข Published
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque
Paper โข 2506.07597 โข Published