open/ acc

community

AI & ML interests

None defined yet.

Recent Activity

open-acc's activity

prithivMLmods 
posted an update about 3 hours ago
burtenshaw 
posted an update about 9 hours ago
view post
Post
426
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.
  • 1 reply
·
clem 
posted an update about 24 hours ago
view post
Post
1410
We just crossed 1,500,000 public models on Hugging Face (and 500k spaces, 330k datasets, 50k papers). One new repository is created every 15 seconds. Congratulations all!
  • 1 reply
·
csabakecskemeti 
posted an update 1 day ago
burtenshaw 
posted an update 1 day ago
view post
Post
813
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
burtenshaw 
posted an update 1 day ago
view post
Post
1154
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

git+https://github.com/huggingface/transformers@main
git+https://github.com/huggingface/trl.git@main
bitsandbytes
peft


plus this with --no-deps

git+https://github.com/unslothai/unsloth-zoo.git@nightly
git+https://github.com/unslothai/unsloth.git@nightly


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.

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
·
AtAndDev 
posted an update 2 days ago
view post
Post
1338
Gemma 3 seems to be really good at human preference. Just waiting for ppl to see it.
prithivMLmods 
posted an update 2 days ago
burtenshaw 
posted an update 2 days ago
view post
Post
1602
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
·
julien-c 
posted an update 3 days ago
view post
Post
2131
Important notice 🚨

For Inference Providers who have built support for our Billing API (currently: Fal, Novita, HF-Inference – with more coming soon), we've started enabling Pay as you go (=PAYG)

What this means is that you can use those Inference Providers beyond the free included credits, and they're charged to your HF account.

You can see it on this view: any provider that does not have a "Billing disabled" badge, is PAYG-compatible.
prithivMLmods 
posted an update 3 days ago
BrigitteTousi 
posted an update 3 days ago
BrigitteTousi 
posted an update 4 days ago
view post
Post
3606
Regardless of X being down or not, so glad I can rely on HF Posts for AI news ❤️🤗
  • 1 reply
·
clem 
posted an update 6 days ago
view post
Post
7000
I was chatting with @peakji , one of the cofounders of Manu AI, who told me he was on Hugging Face (very cool!).

He shared an interesting insight which is that agentic capabilities might be more of an alignment problem rather than a foundational capability issue. Similar to the difference between GPT-3 and InstructGPT, some open-source foundation models are simply trained to 'answer everything in one response regardless of the complexity of the question' - after all, that's the user preference in chatbot use cases. Just a bit of post-training on agentic trajectories can make an immediate and dramatic difference.

As a thank you to the community, he shared 100 invite code first-come first serve, just use “HUGGINGFACE” to get access!
·
csabakecskemeti 
posted an update 7 days ago
view post
Post
790
Fine tuning on the edge. Pushing the MI100 to it's limits.
QWQ-32B 4bit QLORA fine tuning
VRAM usage 31.498G/31.984G :D

  • 3 replies
·
clem 
posted an update 7 days ago
prithivMLmods 
posted an update 9 days ago
burtenshaw 
posted an update 9 days ago
view post
Post
3554
I’m super excited to work with @mlabonne to build the first practical example in the reasoning course.

🔗 https://huggingface.co/reasoning-course

Here's a quick walk through of the first drop of material that works toward the use case:

- a fundamental introduction to reinforcement learning. Answering questions like, ‘what is a reward?’ and ‘how do we create an environment for a language model?’

- Then it focuses on Deepseek R1 by walking through the paper and highlighting key aspects. This is an old school way to learn ML topics, but it always works.

- Next, it takes to you Transformers Reinforcement Learning and demonstrates potential reward functions you could use. This is cool because it uses Marimo notebooks to visualise the reward.

- Finally, Maxime walks us through a real training notebook that uses GRPO to reduce generation length. I’m really into this because it works and Maxime took the time to validate it share assets and logging from his own runs for you to compare with.

Maxime’s work and notebooks have been a major part of the open source community over the last few years. I, like everyone, have learnt so much from them.
clem 
posted an update 10 days ago
view post
Post
5872
Super happy to welcome Nvidia as our latest enterprise hub customer. They have almost 2,000 team members using Hugging Face, and close to 20,000 followers of their org. Can't wait to see what they'll open-source for all of us in the coming months!

Nvidia's org: https://huggingface.co/nvidia
Enterprise hub: https://huggingface.co/enterprise
csabakecskemeti 
posted an update 13 days ago
view post
Post
1938
-UPDATED-
4bit inference is working! The blogpost is updated with code snippet and requirements.txt
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
-UPDATED-
I've played around with an MI100 and ROCm and collected my experience in a blogpost:
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.
  • 4 replies
·