TAROT: Test-driven and Capability-adaptive Curriculum Reinforcement Fine-tuning for Code Generation with Large Language Models
Paper
• 2602.15449 • Published
• 6
AI & ML interests
Instruction tuning, Diffusion models
Recent Activity
sayakpaul
authored a paper 6 days ago
sayakpaul
authored a paper 5 months ago
Post
2386
Fast LoRA inference for Flux with Diffusers and PEFT 🚨
There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.
In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:
1.
2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯
We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗
Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.
Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
There are great materials that demonstrate how to optimize inference for popular image generation models, such as Flux. However, very few cover how to serve LoRAs fast, despite LoRAs being an inseparable part of their adoption.
In our latest post, @BenjaminB and I show different techniques to optimize LoRA inference for the Flux family of models for image generation. Our recipe includes the use of:
1.
torch.compile2. Flash Attention 3 (when compatible)
3. Dynamic FP8 weight quantization (when compatible)
4. Hotswapping for avoiding recompilation during swapping new LoRAs 🤯
We have tested our recipe with Flux.1-Dev on both H100 and RTX 4090. We achieve at least a *2x speedup* in either of the GPUs. We believe our recipe is grounded in the reality of how LoRA-based use cases are generally served. So, we hope this will be beneficial to the community 🤗
Even though our recipe was tested primarily with NVIDIA GPUs, it should also work with AMD GPUs.
Learn the details and the full code here:
https://huggingface.co/blog/lora-fast
- 3 replies
Post
2960
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
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
-
- 2 replies
Post
1898
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.
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 2 papers 10 months ago
Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
Paper
• 2505.10046 • Published
• 9
From Reflection to Perfection: Scaling Inference-Time Optimization for Text-to-Image Diffusion Models via Reflection Tuning
Paper
• 2504.16080 • Published
• 15
sayakpaul
authored a paper 12 months ago
Post
3971
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 (
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/ 🤗
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/ 🤗
Post
2174
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
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: 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
Post
2095
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
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
Post
4506
Commits speak louder than words 🤪
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release 🤗
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
* 4 new video models
* Multiple image models, including SANA & Flux Control
* New quantizers -> GGUF & TorchAO
* New training scripts
Enjoy this holiday-special Diffusers release 🤗
Notes: https://github.com/huggingface/diffusers/releases/tag/v0.32.0
Post
2317
In the past seven days, the Diffusers team has shipped:
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
1. Two new video models
2. One new image model
3. Two new quantization backends
4. Three new fine-tuning scripts
5. Multiple fixes and library QoL improvements
Coffee on me if someone can guess 1 - 4 correctly.
- 1 reply
Post
2227
Introducing a high-quality open-preference dataset to further this line of research for image generation.
Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!
So, we decided to work on one with the community!
Check it out here:
https://huggingface.co/blog/image-preferences
Despite being such an inseparable component for modern image generation, open preference datasets are a rarity!
So, we decided to work on one with the community!
Check it out here:
https://huggingface.co/blog/image-preferences
- 8 replies
Post
2246
The Control family of Flux from @black-forest-labs should be discussed more!
It enables structural controls like ControlNets while being significantly less expensive to run!
So, we're working on a Control LoRA training script 🤗
It's still WIP, so go easy:
https://github.com/huggingface/diffusers/pull/10130
It enables structural controls like ControlNets while being significantly less expensive to run!
So, we're working on a Control LoRA training script 🤗
It's still WIP, so go easy:
https://github.com/huggingface/diffusers/pull/10130
sayakpaul
authored a paper about 1 year ago
Post
1603
Let 2024 be the year of video model fine-tunes!
Check it out here:
https://github.com/a-r-r-o-w/cogvideox-factory/tree/main/training/mochi-1
Check it out here:
https://github.com/a-r-r-o-w/cogvideox-factory/tree/main/training/mochi-1
Post
2762
It's been a while we shipped native quantization support in
We currently support
This post is just a reminder of what's possible:
1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4.
5. Training and loading LoRAs into quantized checkpoints
Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
diffusers 🧨We currently support
bistandbytes as the official backend but using others like torchao is already very simple. This post is just a reminder of what's possible:
1. Loading a model with a quantization config
2. Saving a model with quantization config
3. Loading a pre-quantized model
4.
enable_model_cpu_offload()5. Training and loading LoRAs into quantized checkpoints
Docs:
https://huggingface.co/docs/diffusers/main/en/quantization/bitsandbytes
- 1 reply
Post
2833
Did some little experimentation to resize pre-trained LoRAs on Flux. I explored two themes:
* Decrease the rank of a LoRA
* Increase the rank of a LoRA
The first one is helpful in reducing memory requirements if the LoRA is of a high rank, while the second one is merely an experiment. Another implication of this study is in the unification of LoRA ranks when you would like to
Check it out here:
sayakpaul/flux-lora-resizing
* Decrease the rank of a LoRA
* Increase the rank of a LoRA
The first one is helpful in reducing memory requirements if the LoRA is of a high rank, while the second one is merely an experiment. Another implication of this study is in the unification of LoRA ranks when you would like to
torch.compile() them. Check it out here:
sayakpaul/flux-lora-resizing
- 1 reply
sayakpaul
authored a paper over 1 year ago