Yay! Organizations can now publish blog Articles
•
36
Hugging Face
Enterprise
company
Verified
AI & ML interests
The AI community building the future.
Recent Activity
Articles
huggingface's activity
sayakpaul
updated
a
dataset
about 16 hours ago
evijit
updated
a
dataset
about 18 hours ago
nielsr
updated
a
Space
about 22 hours ago
jsulz
updated
a
dataset
1 day ago
[FEEDBACK] Follow
14
#14 opened over 1 year ago
by
victor
mishig
updated
a
Space
1 day ago
burtenshaw
posted
an
update
2 days ago
Post
1533
The open LLM leaderboard is completed, retired, dead, ‘ascended to a higher plane’. And in its shadow we have an amazing range of leaderboards built and maintained by the community.
In this post, I just want to list some of those great leaderboards that you should bookmark for staying up to date:
- Chatbot Arena LLM Leaderboard is the first port of call for checking out the best model. It’s not the fastest because humans will need to use the models to get scores, but it’s worth the wait. lmarena-ai/chatbot-arena-leaderboard
- OpenVLM Leaderboard is great for getting scores on vision language models opencompass/open_vlm_leaderboard
- Ai2 are doing a great job on RewardBench and I hope they keep it up because reward models are the unsexy workhorse of the field. allenai/reward-bench
- The GAIA leaderboard is great for evaluating agent applications. gaia-benchmark/leaderboard
🤩 This seems like such a sustainable way of building for the long term, where rather than leaning on a single company to evaluate all LLMs, we share the load.
In this post, I just want to list some of those great leaderboards that you should bookmark for staying up to date:
- Chatbot Arena LLM Leaderboard is the first port of call for checking out the best model. It’s not the fastest because humans will need to use the models to get scores, but it’s worth the wait. lmarena-ai/chatbot-arena-leaderboard
- OpenVLM Leaderboard is great for getting scores on vision language models opencompass/open_vlm_leaderboard
- Ai2 are doing a great job on RewardBench and I hope they keep it up because reward models are the unsexy workhorse of the field. allenai/reward-bench
- The GAIA leaderboard is great for evaluating agent applications. gaia-benchmark/leaderboard
🤩 This seems like such a sustainable way of building for the long term, where rather than leaning on a single company to evaluate all LLMs, we share the load.
- 3 replies
sayakpaul
authored
a
paper
2 days ago
Post
505
🤯 Gemma 3's image analysis blew me away!
Tested 2 ways to extract airplane registration numbers from photos with 12B model:
1️⃣ Gradio app w/API link (underrated feature IMO) + ZeroGPU infra on Hugging Face in Google Colab. Fast & free.
2️⃣ LMStudio + local processing (100% private). Running this powerhouse on a MacBook w/16GB RAM is wild! 🚀
Colab: https://colab.research.google.com/drive/1YmmaP0IDEu98CLDppAAK9kbQZ7lFnLZ1?usp=sharing
Tested 2 ways to extract airplane registration numbers from photos with 12B model:
1️⃣ Gradio app w/API link (underrated feature IMO) + ZeroGPU infra on Hugging Face in Google Colab. Fast & free.
2️⃣ LMStudio + local processing (100% private). Running this powerhouse on a MacBook w/16GB RAM is wild! 🚀
Colab: https://colab.research.google.com/drive/1YmmaP0IDEu98CLDppAAK9kbQZ7lFnLZ1?usp=sharing
Post
1474
SEA-VL🔥 an OPEN dataset bridge the AI culture gap in Southeast Asia!
Paper: Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia (2503.07920)
✨1.28M+ culturally relevant images
✨85% accuracy in auto-collected images
✨Tracking underrepresented SEA languages & traditions
Paper: Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asia (2503.07920)
✨1.28M+ culturally relevant images
✨85% accuracy in auto-collected images
✨Tracking underrepresented SEA languages & traditions
burtenshaw
posted
an
update
3 days ago
Post
1600
Still speed running Gemma 3 to think. Today I focused on setting up gpu poor hardware to run GRPO.
This is a plain TRL and PEFT notebook which works on mac silicone or colab T4. This uses the 1b variant of Gemma 3 and a reasoning version of GSM8K dataset.
🧑🍳 There’s more still in the oven like releasing models, an Unsloth version, and deeper tutorials, but hopefully this should bootstrap your projects.
Here’s a link to the 1b notebook: https://colab.research.google.com/drive/1mwCy5GQb9xJFSuwt2L_We3eKkVbx2qSt?usp=sharing
This is a plain TRL and PEFT notebook which works on mac silicone or colab T4. This uses the 1b variant of Gemma 3 and a reasoning version of GSM8K dataset.
🧑🍳 There’s more still in the oven like releasing models, an Unsloth version, and deeper tutorials, but hopefully this should bootstrap your projects.
Here’s a link to the 1b notebook: https://colab.research.google.com/drive/1mwCy5GQb9xJFSuwt2L_We3eKkVbx2qSt?usp=sharing
- 1 reply
burtenshaw
posted
an
update
3 days ago
Post
1535
everybody and their dog is fine-tuning Gemma 3 today, so I thought I'd do a longer post on the tips and sharp edges I find. let's go!
1. has to be install everything form main and nightly. this is what I'm working with to get unsloth and TRL running
plus this with
2. will brown's code to turn GSM8k into a reasoning dataset is a nice toy experiment https://gist.github.com/willccbb/4676755236bb08cab5f4e54a0475d6fb
3. with a learning rate of 5e-6 rewards and loss stayed flat for the first 100 or so steps.
4. so far none of my runs have undermined the outputs after 1 epoch. therefore, I'm mainly experimenting with bigger LoRA adapters.
5. vision fine-tuning isn't available in TRL's GRPOTrainer, so stick to text datasets. but no need to load the model differently in transformers or Unsloth
if you want an introduction to GRPO, check out the reasoning course, it walks you through the algorithm, theory, and implementation in a smooth way.
https://huggingface.co/reasoning-course
1. has to be install everything form main and nightly. this is what I'm working with to get unsloth and TRL running
git+https://github.com/huggingface/transformers@main
git+https://github.com/huggingface/trl.git@main
bitsandbytes
peftplus this with
--no-depsgit+https://github.com/unslothai/unsloth-zoo.git@nightly
git+https://github.com/unslothai/unsloth.git@nightly2. will brown's code to turn GSM8k into a reasoning dataset is a nice toy experiment https://gist.github.com/willccbb/4676755236bb08cab5f4e54a0475d6fb
3. with a learning rate of 5e-6 rewards and loss stayed flat for the first 100 or so steps.
4. so far none of my runs have undermined the outputs after 1 epoch. therefore, I'm mainly experimenting with bigger LoRA adapters.
from trl import GRPOConfig
training_args = GRPOConfig(
learning_rate = 5e-6,
adam_beta1 = 0.9,
adam_beta2 = 0.99,
weight_decay = 0.1,
warmup_ratio = 0.1,
lr_scheduler_type = "cosine",
optim = "adamw_8bit",
logging_steps = 1,
per_device_train_batch_size = 2,
gradient_accumulation_steps = 1,
num_generations = 2,
max_prompt_length = 256,
max_completion_length = 1024 - 256,
num_train_epochs = 1,
max_steps = 250,
save_steps = 250,
max_grad_norm = 0.1,
report_to = "none",
)5. vision fine-tuning isn't available in TRL's GRPOTrainer, so stick to text datasets. but no need to load the model differently in transformers or Unsloth
from transformers import AutoModelForImageTextToText
model = AutoModelForImageTextToText.from_pretrained("google/gemma-3-4b-it)if you want an introduction to GRPO, check out the reasoning course, it walks you through the algorithm, theory, and implementation in a smooth way.
https://huggingface.co/reasoning-course
-
- 2 replies
Post
1709
Open Sora 2.0 is out 🔥
hpcai-tech/open-sora-20-67cfb7efa80a73999ccfc2d5
✨ 11B with Apache2.0
✨ Low training cost - $200k
✨ open weights, code and training workflow
hpcai-tech/open-sora-20-67cfb7efa80a73999ccfc2d5
✨ 11B with Apache2.0
✨ Low training cost - $200k
✨ open weights, code and training workflow
Upload folder using huggingface_hub
1
#450 opened 4 days ago
by
a-r-r-o-w
Post
1141
Ever wanted 45 min with one of AI’s most fascinating minds? Was with
@thomwolf
at HumanX Vegas. Sharing my notes of his Q&A with the press—completely changed how I think about AI’s future:
1️⃣ The next wave of successful AI companies won’t be defined by who has the best model but by who builds the most useful real-world solutions. "We all have engines in our cars, but that’s rarely the only reason we buy one. We expect it to work well, and that’s enough. LLMs will be the same."
2️⃣ Big players are pivoting: "Closed-source companies—OpenAI being the first—have largely shifted from LLM announcements to product announcements."
3️⃣ Open source is changing everything: "DeepSeek was open source AI’s ChatGPT moment. Basically, everyone outside the bubble realized you can get a model for free—and it’s just as good as the paid ones."
4️⃣ Product innovation is being democratized: Take Manus, for example—they built a product on top of Anthropic’s models that’s "actually better than Anthropic’s own product for now, in terms of agents." This proves that anyone can build great products with existing models.
We’re entering a "multi-LLM world," where models are becoming commoditized, and all the tools to build are readily available—just look at the flurry of daily new releases on Hugging Face.
Thom's comparison to the internet era is spot-on: "In the beginning you made a lot of money by making websites... but nowadays the huge internet companies are not the companies that built websites. Like Airbnb, Uber, Facebook, they just use the internet as a medium to make something for real life use cases."
Love to hear your thoughts on this shift!
1️⃣ The next wave of successful AI companies won’t be defined by who has the best model but by who builds the most useful real-world solutions. "We all have engines in our cars, but that’s rarely the only reason we buy one. We expect it to work well, and that’s enough. LLMs will be the same."
2️⃣ Big players are pivoting: "Closed-source companies—OpenAI being the first—have largely shifted from LLM announcements to product announcements."
3️⃣ Open source is changing everything: "DeepSeek was open source AI’s ChatGPT moment. Basically, everyone outside the bubble realized you can get a model for free—and it’s just as good as the paid ones."
4️⃣ Product innovation is being democratized: Take Manus, for example—they built a product on top of Anthropic’s models that’s "actually better than Anthropic’s own product for now, in terms of agents." This proves that anyone can build great products with existing models.
We’re entering a "multi-LLM world," where models are becoming commoditized, and all the tools to build are readily available—just look at the flurry of daily new releases on Hugging Face.
Thom's comparison to the internet era is spot-on: "In the beginning you made a lot of money by making websites... but nowadays the huge internet companies are not the companies that built websites. Like Airbnb, Uber, Facebook, they just use the internet as a medium to make something for real life use cases."
Love to hear your thoughts on this shift!
- 1 reply
abidlabs
updated
a
dataset
4 days ago
burtenshaw
posted
an
update
4 days ago
Post
1694
Here’s a notebook to make Gemma reason with GRPO & TRL. I made this whilst prepping the next unit of the reasoning course:
In this notebooks I combine together google’s model with some community tooling
- First, I load the model from the Hugging Face hub with transformers’s latest release for Gemma 3
- I use PEFT and bitsandbytes to get it running on Colab
- Then, I took Will Browns processing and reward functions to make reasoning chains from GSM8k
- Finally, I used TRL’s GRPOTrainer to train the model
Next step is to bring Unsloth AI in, then ship it in the reasoning course. Links to notebook below.
https://colab.research.google.com/drive/1Vkl69ytCS3bvOtV9_stRETMthlQXR4wX?usp=sharing
In this notebooks I combine together google’s model with some community tooling
- First, I load the model from the Hugging Face hub with transformers’s latest release for Gemma 3
- I use PEFT and bitsandbytes to get it running on Colab
- Then, I took Will Browns processing and reward functions to make reasoning chains from GSM8k
- Finally, I used TRL’s GRPOTrainer to train the model
Next step is to bring Unsloth AI in, then ship it in the reasoning course. Links to notebook below.
https://colab.research.google.com/drive/1Vkl69ytCS3bvOtV9_stRETMthlQXR4wX?usp=sharing
- 3 replies
lewtun
authored
a
paper
4 days ago
Post
1376
Google just dropped an exciting technical report for the brand-new Gemma3 model! 🚀 Here are my personal notes highlighting the most intriguing architectural innovations, design choices, and insights from this release:
1) Architecture choices:
> No more softcaping, replace by QK-Norm
> Both Pre AND Post Norm
> Wider MLP than Qwen2.5, ~ same depth
> SWA with 5:1 and 1024 (very small and cool ablation on the paper!)
> No MLA to save KV cache, SWA do the job!
2) Long context
> Only increase the rope in the global layer (to 1M)
> Confirmation that it's harder to do long context for smol models, no 128k for the 1B
> Pretrained with 32k context? seems very high
> No yarn nor llama3 like rope extension
3) Distillation
> Only keep te first 256 logits for the teacher
> Ablation on the teacher gap (tl;dr you need some "patience" to see that using a small teacher is better)
> On policy distillation yeahh (by
@agarwl_
et al), not sure if the teacher gap behave the same here, curious if someone have more info?
4) Others
> Checkpoint with QAT, that's very cool
> RL using improve version of BOND, WARM/WARP good excuse to look at
@ramealexandre
papers
> Only use Zero3, no TP/PP if i understand correctly ?
> Training budget relatively similar than gemma2
1) Architecture choices:
> No more softcaping, replace by QK-Norm
> Both Pre AND Post Norm
> Wider MLP than Qwen2.5, ~ same depth
> SWA with 5:1 and 1024 (very small and cool ablation on the paper!)
> No MLA to save KV cache, SWA do the job!
2) Long context
> Only increase the rope in the global layer (to 1M)
> Confirmation that it's harder to do long context for smol models, no 128k for the 1B
> Pretrained with 32k context? seems very high
> No yarn nor llama3 like rope extension
3) Distillation
> Only keep te first 256 logits for the teacher
> Ablation on the teacher gap (tl;dr you need some "patience" to see that using a small teacher is better)
> On policy distillation yeahh (by
@agarwl_
et al), not sure if the teacher gap behave the same here, curious if someone have more info?
4) Others
> Checkpoint with QAT, that's very cool
> RL using improve version of BOND, WARM/WARP good excuse to look at
@ramealexandre
papers
> Only use Zero3, no TP/PP if i understand correctly ?
> Training budget relatively similar than gemma2
- 1 reply
Post
1210
Spark TTS 🔊New OPEN TTS model that can generate any voice with just seconds of audio!
Released by SparkAudio community🔥
Model👉 SparkAudio/Spark-TTS-0.5B
Paper👉 Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens (2503.01710)
✨ Supports English & Chinese
✨ BiCodec Speech Codec: Enables precise voice control by separating semantics & speaker attributes
Released by SparkAudio community🔥
Model👉 SparkAudio/Spark-TTS-0.5B
Paper👉 Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens (2503.01710)
✨ Supports English & Chinese
✨ BiCodec Speech Codec: Enables precise voice control by separating semantics & speaker attributes