Post
1044
What's currently the biggest gap in Open Source Datasets ??
- 4 replies
appvoid
appvoid
AI & ML interests
training small language models aiming to high-quality text | fine-tuning + merging expert
check out gumroad for future ai products!
Recent Activity
published
a model
about 1 month ago
appvoid/arco-2-Q8_0-GGUF
Organizations
reacted to
KingNish's
post with ๐
about 1 month ago
char level text editing
posted
an
update
about 1 month ago
Post
248
have you ever wanted to quickly prototype an idea with a language model but get intimidated by the whole setup? no issues! now you can try building a custom one from scratch!
beware, it might be addictive once you learn how it works: https://nohak.pythonanywhere.com/
beware, it might be addictive once you learn how it works: https://nohak.pythonanywhere.com/
reacted to
victor's
post with โค๏ธ
6 months ago
Post
6286
Hey everyone, we've given https://hf.co/spaces page a fresh update!
Smart Search: Now just type what you want to doโlike "make a viral meme" or "generate music"โand our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
Weโd love to hear what you thinkโdrop us some feedback plz!
Smart Search: Now just type what you want to doโlike "make a viral meme" or "generate music"โand our search gets it.
New Categories: Check out the cool new filter bar with icons to help you pick a category fast.
Redesigned Space Cards: Reworked a bit to really show off the app descriptions, so you know what each Space does at a glance.
Random Prompt: Need ideas? Hit the dice button for a burst of inspiration.
Weโd love to hear what you thinkโdrop us some feedback plz!
-
- 6 replies
reacted to
lamhieu's
post with ๐
6 months ago
Post
2246
๐ Unlock the power of a completely free, unlimited multilingual API!
๐ The Lightweight Embeddings API offers state-of-the-art text and image embeddings, advanced reranking, and seamless support for over 100 languages โ no limits, no restrictions.
๐ Try it now: lamhieu/lightweight-embeddings
๐ The Lightweight Embeddings API offers state-of-the-art text and image embeddings, advanced reranking, and seamless support for over 100 languages โ no limits, no restrictions.
๐ Try it now: lamhieu/lightweight-embeddings
reacted to
KnutJaegersberg's
post with ๐
8 months ago
Post
1380
Intelligence Potentiation: An Evolutionary Perspective on AI Agent Designs
I found it useful to think of AI agent design as progressing up a ladder, through evolutionary selection.
https://huggingface.co/blog/KnutJaegersberg/intelligence-potentiation
I found it useful to think of AI agent design as progressing up a ladder, through evolutionary selection.
https://huggingface.co/blog/KnutJaegersberg/intelligence-potentiation
reacted to
alielfilali01's
post with ๐ค
8 months ago
Post
3551
Unpopular opinion: Open Source takes courage to do !
Not everyone is brave enough to release what they have done (the way they've done it) to the wild to be judged !
It really requires a high level of "knowing wth are you doing" ! It's kind of a super power !
Cheers to the heroes here who see this!
Not everyone is brave enough to release what they have done (the way they've done it) to the wild to be judged !
It really requires a high level of "knowing wth are you doing" ! It's kind of a super power !
Cheers to the heroes here who see this!
-
- 5 replies
reacted to
merve's
post with ๐ฅ
9 months ago
Post
5400
OmniVision-968M: a new local VLM for edge devices, fast & small but performant
๐จ a new vision language model with 9x less image tokens, super efficient
๐ aligned with DPO for reducing hallucinations
โก๏ธ Apache 2.0 license ๐ฅ
Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model https://huggingface.co/NexaAIDev/omnivision-968M
๐จ a new vision language model with 9x less image tokens, super efficient
๐ aligned with DPO for reducing hallucinations
โก๏ธ Apache 2.0 license ๐ฅ
Demo hf.co/spaces/NexaAIDev/omnivlm-dpo-demo
Model https://huggingface.co/NexaAIDev/omnivision-968M
- 4 replies
reacted to
m-ric's
post with ๐
9 months ago
Post
1644
๐๐ป๐ฑ๐ฟ๐ผ๐ถ๐ฑ๐๐ฎ๐ฏ: ๐๐ถ๐ฟ๐๐ ๐ฒ๐๐ฒ๐ฟ ๐๐๐๐๐ฒ๐บ๐ฎ๐๐ถ๐ฐ ๐ฏ๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ ๐ณ๐ผ๐ฟ ๐๐ป๐ฑ๐ฟ๐ผ๐ถ๐ฑ ๐บ๐ผ๐ฏ๐ถ๐น๐ฒ ๐ฎ๐ด๐ฒ๐ป๐๐ ๐๐ต๐ผ๐๐ ๐๐ต๐ฎ๐ ๐๐บ๐ฎ๐น๐น, ๐ณ๐ถ๐ป๐ฒ-๐๐๐ป๐ฒ๐ฑ ๐ผ๐ฝ๐ฒ๐ป ๐บ๐ผ๐ฑ๐ฒ๐น๐ ๐ฐ๐ฎ๐ป ๐ฝ๐ผ๐๐ฒ๐ฟ ๐ฎ ๐๐๐ฅ๐ฉ๐๐ฆ ๐๐๐๐๐ฒ๐บ ๐ผ๐ป ๐๐ผ๐๐ฟ ๐๐บ๐ฎ๐ฟ๐๐ฝ๐ต๐ผ๐ป๐ฒ ๐ฑ๐ฅ
A team from Tsinghua University just released AndroidLab, the first systematic framework to evaluate and train Android mobile agents that works with both text-only and multimodal models.
They show that fine-tuning small open-source models can significantly boost performance, matching that of much bigger closed models like GPT-4o.
The team built:
๐ย A reproducible benchmark with 138 tasks across 9 apps to evaluate mobile agents systematically
๐๐ฑย A framework supporting both text-only (via XML) and visual (via marked screenshots) interfaces
โ ย An instruction dataset of 10.5k operation traces for training mobile agents
Key insights:
- ๐ Fine-tuning improves performance BY A LOT: Open-source model Llama-3.1-8B improves from 2% to 24% success rate after training, nearly reaching GPT-4o performance although itโs much smaller
- โ๏ธ Text-only agents match multimodal ones: XML-based agents achieve similar performance to screenshot-based multimodal agents.
Read their paper here ๐ AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2410.24024)
A team from Tsinghua University just released AndroidLab, the first systematic framework to evaluate and train Android mobile agents that works with both text-only and multimodal models.
They show that fine-tuning small open-source models can significantly boost performance, matching that of much bigger closed models like GPT-4o.
The team built:
๐ย A reproducible benchmark with 138 tasks across 9 apps to evaluate mobile agents systematically
๐๐ฑย A framework supporting both text-only (via XML) and visual (via marked screenshots) interfaces
โ ย An instruction dataset of 10.5k operation traces for training mobile agents
Key insights:
- ๐ Fine-tuning improves performance BY A LOT: Open-source model Llama-3.1-8B improves from 2% to 24% success rate after training, nearly reaching GPT-4o performance although itโs much smaller
- โ๏ธ Text-only agents match multimodal ones: XML-based agents achieve similar performance to screenshot-based multimodal agents.
Read their paper here ๐ AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2410.24024)
reacted to
KnutJaegersberg's
post with ๐ค
10 months ago
Post
2245
Wrote a blog post with some ideas about prompt engineering
https://huggingface.co/blog/KnutJaegersberg/first-principles-prompt-engineering
https://huggingface.co/blog/KnutJaegersberg/first-principles-prompt-engineering
posted
an
update
10 months ago
Post
1496
If someone would like to keep pushing the limits of what's possible on cpu while being efficient/fast, here's my un-trained arco model scaled-up to 770m parameters. Consider it a modern gpt-2-large to experiment with
appvoid/arco-plus
appvoid/arco-plus
replied to
their
post
10 months ago
How long did it take to reply and what are your context window limits? Model type?
it takes 3-5 seconds to reply when the prompt is longer than 30-50 words on average but it increases linearly with number of tokens in the prompt, the one on the picture is llama 3 1b but the one i'm using right now is arco 2 which is a llama model, cannot keep any kind of general knowledge, i noticed with qwen 2 (and later confirmed with meta's model) that you don't need a lot of parameters to get general knowledge, you just need tons of data
posted
an
update
10 months ago
Post
3508
700m parameters are the sweet spot for cpu usage, please let's make more of those!
-
- 2 replies
posted
an
update
10 months ago
Post
1827
meta just released 1b parameters model and to honor it i released arco 2 just in time for the fine-tuners to tweak around, enjoy these small powerful language models!!!
meta-llama/Llama-3.2-1B
appvoid/arco-2
meta-llama/Llama-3.2-1B
appvoid/arco-2
- 1 reply
posted
an
update
11 months ago
Post
763
WHY ARE THERE NOT TEXT FEWSHOT DATASETS @ HUGGINGFACE? ๐ฒ
reacted to
zolicsaki's
post with ๐ฅ
11 months ago
Post
1342
Fast inference is no longer a nice-to-have demo; it will be the driving force behind future frontier models. Time to switch over to custom AI hardware and short Nvidia.
Try out SambaNova's lightning fast API for free at https://sambanova.ai/fast-api?api_ref=444868
Try out SambaNova's lightning fast API for free at https://sambanova.ai/fast-api?api_ref=444868
reacted to
KnutJaegersberg's
post with โค๏ธ
11 months ago
Post
1176
appvoid/arco
arco consistently outperforms every sota model below 600m parameters on average
appvoid/arco
arco consistently outperforms every sota model below 600m parameters on average
appvoid/arco
posted
an
update
11 months ago
Post
1285
i just made the best 0.5b model to date (again)
its name is arco and is ready to fight any 0.5b model at arc challenge
appvoid/arco
its name is arco and is ready to fight any 0.5b model at arc challenge
appvoid/arco
as a model-tweaker is such a huge relief to know we have hf for years to come
reacted to
clem's
post with โค๏ธ
12 months ago
Post
3867
This isnโt a goal of ours because we have plenty of money in the bank but quite excited to see that
@huggingfaceis
profitable these days, with 220 team members and most of our platform being free (like model hosting) and open-source for the community!
Especially noteworthy at a time when most AI startups wouldnโt survive a year or two without VC money. Yay!
Especially noteworthy at a time when most AI startups wouldnโt survive a year or two without VC money. Yay!
-
- 4 replies