coding-assistant-custom (Personal Coding Assistant)

sayakpaul

posted an update 6 days ago

Post

2215

Diffusers supports a good variety of quantization backends. It can be challenging to navigate through them, given the complex nature of diffusion pipelines in general.

So, @derekl35 set out to write a comprehensive guide that puts users in the front seat. Explore the different backends we support, learn the trade-offs they offer, and finally, check out the cool space we built that lets you compare quantization results.

Give it a go here:
https://lnkd.in/gf8Pi4-2

sayakpaul

posted an update 7 days ago

Post

1626

Despite the emergence of combining LLM and DiT architectures for T2I synthesis, its design remains severely understudied.

This was done long ago and got into CVPR25 -- super excited to finally share it now, along with the data and code ♥️

We explore several architectural choices that affect this design. We provide an open & reproducible training recipe that works at scale.

Works like Playground v3 have already explored a deep fusion between an LLM and a DiT, sharing their representations through layerwise attention. They exhibit excellent performance on T2I.

Despite its compelling results and other performance virtues, it remains unexplored, which is what we want to improve in our work. Specifically, we take a pre-trained LLM (Gemma-2B) and trainable DiT, and set out to explore what makes a "good deep fusion" between the two for T2I.

We explore several key questions in the work, such as:

Q1: How should we do attention? We considered several alternatives. PixArt-Alpha like attention (cross-attention) is very promising.
Q2: Should we incorporate additional text modulation?
Q3: Can we eliminate timestep conditioning?
Q4: How do we do positional encodings?
Q5: Do instruction-tuned LLMs help deep fusion?
Q6: Would using a decoder LLM from a multimodal model be helpful?
Q7: Does using a better variant of Gemma help?

Based on the above findings, we arrive at FuseDiT with the following components on top of the base architecture from the findings of our experiments.

* No AdaLN-Zero modules
* 1D + 2D-RoPE
* Gemma 2 2B, adjusting DiT configurations accordingly

We trained FuseDiT on a mixture from CC12M, JourneyDB, & SA (~26M image-text pairs) for 800 steps. While not the best model, it's encouraging to develop something in a guided manner using open datasets.

To know more (code, models, all are available), please check out the paper:
https://lnkd.in/gg6qyqZX.

sayakpaul

authored a paper 11 days ago

Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis

Paper • 2505.10046 • Published 13 days ago • 9

sayakpaul

authored a paper about 1 month ago

From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning

Paper • 2504.16080 • Published Apr 22 • 15

lvwerra

authored a paper about 2 months ago

SmolVLM: Redefining small and efficient multimodal models

Paper • 2504.05299 • Published Apr 7 • 185

chansung

posted an update 2 months ago

Post

3717

simple guide on the recipe for GRPO on Open-R1 which is built on top of TRL

I think FastAPI wrapper of vLLM with WeightSyncWorker is pretty cool feature. Also, we have many predefined reward functions out of the box!

5 replies

·

chansung

posted an update 2 months ago

Post

2643

Mistral AI Small 3.1 24B is not only commercial free but also the best model in a single GPU deployment.

I packed up all the information you need to know in a single picture. Hope this helps! :)

1 reply

·

sayakpaul

authored a paper 2 months ago

SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation

Paper • 2503.09641 • Published Mar 12 • 39

chansung

posted an update 3 months ago

Post

1580

Gemma 3 Release in a nutshell
(seems like function calling is not supported whereas the announcement said so)

sayakpaul

posted an update 3 months ago

Post

3851

Inference-time scaling meets Flux.1-Dev (and others) 🔥

Presenting a simple re-implementation of "Inference-time scaling diffusion models beyond denoising steps" by Ma et al.

I did the simplest random search strategy, but results can potentially be improved with better-guided search methods.

Supports Gemini 2 Flash & Qwen2.5 as verifiers for "LLMGrading" 🤗

The steps are simple:

For each round:

1> Starting by sampling 2 starting noises with different seeds.
2> Score the generations w.r.t a metric.
3> Obtain the best generation from the current round.

If you have more compute budget, go to the next search round. Scale the noise pool (2 ** search_round) and repeat 1 - 3.

This constitutes the random search method as done in the paper by Google DeepMind.

Code, more results, and a bunch of other stuff are in the repository. Check it out here: https://github.com/sayakpaul/tt-scale-flux/ 🤗

lvwerra

authored a paper 4 months ago

SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model

Paper • 2502.02737 • Published Feb 4 • 230

chansung

posted an update 4 months ago

Post

3022

Simple Paper Review #5

I briefly reviewed the paper "SFT Memorizes, RL Generalizes," which compares SFT and RL in post-training of LLM/VLM from HKU, UC Berkeley, Google DeepMind, and New York University

The conclusion suggests SFT excels in memorization, while RL is better for generalization. However, since LLM/VLM should benefit humans beyond just generalization, a mix of SFT and RL is advisable. Typically, some SFT is followed by RL to understand prompt formats and enhance generalization through trial and error.

The study focused on one model, Llama-3.2-Vision-11B, using environments like General Points for arithmetic reasoning and V-IRL for spatial reasoning. Training data was used for both SFT and RL, with evaluations on in-distribution and out-of-distribution data to assess memorization and generalization.

I want to apply RL extensively, but it requires building a similar simulation environment. For domain-specific models, significant investment in creating a "playground" for the model is crucial, as the effort will directly influence the outcomes.

https://arxiv.org/abs/2501.17161

chansung

posted an update 4 months ago

Post

4429

A brief summary of the o3-mini

The OpenAI o3-mini model is a significant improvement over the o1-mini, reaching o1 performance levels. While generally good, its performance isn't universally better than previous models (o1, o1-prev.) or GPT-4o across all benchmarks. This means workflows should be re-evaluated with each model upgrade.

The o3-mini has "low," "medium," and "high" versions, with "low" being the base model used for benchmarking. It's speculated that the higher versions simply involve more processing. A fair comparison with other models like Gemini 2.0 Thinking or DeepSeek-R1 would likely need to use the "low" version and a similar "think more" mechanism.

The system card is recommended reading due to its comprehensive benchmark data.

https://openai.com/index/openai-o3-mini/

sayakpaul

posted an update 4 months ago

Post

2103

We have been cooking a couple of fine-tuning runs on CogVideoX with finetrainers, smol datasets, and LoRA to generate cool video effects like crushing, dissolving, etc.

We are also releasing a LoRA extraction utility from a fully fine-tuned checkpoint. I know that kind of stuff has existed since eternity, but the quality on video models was nothing short of spectacular. Below are some links:

* Models and datasets:

finetrainers
* finetrainers: https://github.com/a-r-r-o-w/finetrainers
* LoRA extraction: https://github.com/huggingface/diffusers/blob/main/scripts/extract_lora_from_model.py

1 reply

·

chansung

posted an update 4 months ago

Post

2035

Simple summary on DeepSeek AI's Janus-Pro: A fresh take on multimodal AI!

It builds on its predecessor, Janus, by tweaking the training methodology rather than the model architecture. The result? Improved performance in understanding and generating multimodal data.

Janus-Pro uses a three-stage training strategy, similar to Janus, but with key modifications:
✦ Stage 1 & 2: Focus on separate training for specific objectives, rather than mixing data.
✦ Stage 3: Fine-tuning with a careful balance of multimodal data.

Benchmarks show Janus-Pro holds its own against specialized models like TokenFlow XL and MetaMorph, and other multimodal models like SD3 Medium and DALL-E 3.

The main limitation? Low image resolution (384x384). However, this seems like a strategic choice to focus on establishing a solid "recipe" for multimodal models. Future work will likely leverage this recipe and increased computing power to achieve higher resolutions.

sayakpaul

posted an update 4 months ago

Post

2045

We have authored a post to go over the state of video generation in the Diffusers ecosystem 🧨

We cover the models supported, the knobs of optims our users can fire, fine-tuning, and more 🔥

5-6GBs for HunyuanVideo, sky is the limit 🌌 🤗
https://huggingface.co/blog/video_gen

chansung

posted an update 4 months ago

Post

1740

New look for AI powered paper reviews from the list by Hugging Face Daily Papers ( managed by the @akhaliq )

Bookmark the webpage along, check comprehensive reviews by Google DeepMind Gemini 1.5, and listen to audio podcast made by the same tech used in NotebookLM.

Link: https://deep-diver.github.io/ai-paper-reviewer/

This is not an official service by Hugging Face. It is just a service developed by an individual developer using his own money :)

chansung

posted an update 4 months ago

Post

2044

Simple summarization of Evolving Deeper LLM Thinking (Google DeepMind)

The process starts by posing a question.
1) The LLM generates initial responses.
2) These generated responses are evaluated according to specific criteria (program-based checker).
3) The LLM critiques the evaluated results.
4) The LLM refines the responses based on the evaluation, critique, and original responses.

The refined response is then fed back into step 2). If it meets the criteria, the process ends. Otherwise, the algorithm generates more responses based on the refined ones (with some being discarded, some remaining, and some responses potentially being merged).

Through this process, it demonstrated excellent performance in complex scheduling problems (travel planning, meeting scheduling, etc.). It's a viable method for finding highly effective solutions in specific scenarios.

However, there are two major drawbacks:
🤔 An excessive number of API calls are required. (While the cost might not be very high, it leads to significant latency.)
🤔 The evaluator is program-based. (This limits its use as a general method. It could potentially be modified/implemented using LLM as Judge, but that would introduce additional API costs for evaluation.)

https://arxiv.org/abs/2501.09891

chansung

posted an update 4 months ago

Post

2087

Simple Summarization on DeepSeek-R1 from DeepSeek AI

The RL stage is very important.
↳ However, it is difficult to create a truly helpful AI for people solely through RL.
↳ So, we applied a learning pipeline consisting of four stages: providing a good starting point, reasoning RL, SFT, and safety RL, and achieved performance comparable to o1.
↳ Simply fine-tuning other open models with the data generated by R1-Zero (distillation) resulted in performance comparable to o1-mini.

Of course, this is just a brief overview and may not be of much help. All models are accessible on Hugging Face, and the paper can be read through the GitHub repository.

Model: