arcee-ai/Arcee-Maestro-7B-Preview
Text Generation
β’
Updated
β’
3.65k
β’
32
R T
dingo-actual
AI & ML interests
None yet
Recent Activity
liked
a model
2 days ago
arcee-ai/Arcee-Maestro-7B-Preview
liked
a model
2 days ago
HuggingFaceTB/SmolLM2-1.7B-Instruct-16k
liked
a model
2 days ago
mixedbread-ai/mxbai-rerank-large-v1
Organizations
dingo-actual's activity
liked
3
models
2 days ago
liked
a
model
4 days ago
liked
a
model
5 days ago
reacted to
sayakpaul's
post with π₯
5 days ago
Post
2761
Inference-time scaling meets Flux.1-Dev (and others) π₯
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" π€
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/ π€
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" π€
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/ π€
liked
a
dataset
8 days ago
reacted to
merve's
post with π
8 days ago
Post
4592
Your weekly recap of open AI is here, and it's packed with models!
merve/feb-14-releases-67af876b404cc27c6d837767
π Multimodal
> OpenGVLab released InternVideo 2.5 Chat models, new video LMs with long context
> AIDC released Ovis2 model family along with Ovis dataset, new vision LMs in different sizes (1B, 2B, 4B, 8B, 16B, 34B), with video and OCR support
> ColQwenStella-2b is a multilingual visual retrieval model that is sota in it's size
> Hoags-2B-Exp is a new multilingual vision LM with contextual reasoning, long context video understanding
π¬ LLMs
A lot of math models!
> Open-R1 team released OpenR1-Math-220k large scale math reasoning dataset, along with Qwen2.5-220K-Math fine-tuned on the dataset, OpenR1-Qwen-7B
> Nomic AI released new Nomic Embed multilingual retrieval model, a MoE with 500 params with 305M active params, outperforming other models
> DeepScaleR-1.5B-Preview is a new DeepSeek-R1-Distill fine-tune using distributed RL on math
> LIMO is a new fine-tune of Qwen2.5-32B-Instruct on Math
π£οΈ Audio
> Zonos-v0.1 is a new family of speech recognition models, which contains the model itself and embeddings
πΌοΈ Vision and Image Generation
> We have ported DepthPro of Apple to transformers for your convenience!
> illustrious-xl-v1.0 is a new illustration generation model
π Multimodal
> OpenGVLab released InternVideo 2.5 Chat models, new video LMs with long context
> AIDC released Ovis2 model family along with Ovis dataset, new vision LMs in different sizes (1B, 2B, 4B, 8B, 16B, 34B), with video and OCR support
> ColQwenStella-2b is a multilingual visual retrieval model that is sota in it's size
> Hoags-2B-Exp is a new multilingual vision LM with contextual reasoning, long context video understanding
π¬ LLMs
A lot of math models!
> Open-R1 team released OpenR1-Math-220k large scale math reasoning dataset, along with Qwen2.5-220K-Math fine-tuned on the dataset, OpenR1-Qwen-7B
> Nomic AI released new Nomic Embed multilingual retrieval model, a MoE with 500 params with 305M active params, outperforming other models
> DeepScaleR-1.5B-Preview is a new DeepSeek-R1-Distill fine-tune using distributed RL on math
> LIMO is a new fine-tune of Qwen2.5-32B-Instruct on Math
π£οΈ Audio
> Zonos-v0.1 is a new family of speech recognition models, which contains the model itself and embeddings
πΌοΈ Vision and Image Generation
> We have ported DepthPro of Apple to transformers for your convenience!
> illustrious-xl-v1.0 is a new illustration generation model
- 3 replies
reacted to
burtenshaw's
post with π€
9 days ago
Post
3513
SmolLM2 paper is out! π
π Why do I love it? Because it facilitates teaching and learning!
Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.
- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.
upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)
π Why do I love it? Because it facilitates teaching and learning!
Over the past few months I've engaged with (no joke) thousands of students based on SmolLM.
- People have inferred, fine-tuned, aligned, and evaluated this smol model.
- People used they're own machines and they've used free tools like colab, kaggle, and spaces.
- People tackled use cases in their job, for fun, in their own language, and with their friends.
upvote the paper SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model (2502.02737)
- 1 reply
reacted to
mkurman's
post with π
9 days ago
Post
1577
Blurred-Thoughts Supervised-Finetuning π
After hours of working with GitHub Copilot to organize the code, I'm keen to announce the release of Blurred Thoughts Supervised-Finetuning (BT-SFT), a new method for fine-tuning LLMs to produce more diverse and creative responses.
BT-SFT introduces:
β Smart tokenization method randomly masks tokens within <think> ... </think> tags, promoting the model to generate diverse responses that align better with its probability distribution instead of memorizing the thought process from distilled data.
β Reward function that ensures responses are well-structured.
Explore and contribute to the project available in my GitHub repository:
https://github.com/mkurman/blurred-thoughts-SFT
Keep me updated on your experiments with BT-SFT! π
After hours of working with GitHub Copilot to organize the code, I'm keen to announce the release of Blurred Thoughts Supervised-Finetuning (BT-SFT), a new method for fine-tuning LLMs to produce more diverse and creative responses.
BT-SFT introduces:
β Smart tokenization method randomly masks tokens within <think> ... </think> tags, promoting the model to generate diverse responses that align better with its probability distribution instead of memorizing the thought process from distilled data.
β Reward function that ensures responses are well-structured.
Explore and contribute to the project available in my GitHub repository:
https://github.com/mkurman/blurred-thoughts-SFT
Keep me updated on your experiments with BT-SFT! π
reacted to
schuler's
post with π
9 days ago
Post
7217
π’ New Research Alert: Making Language Models Smaller & Smarter!
Thrilled to share the latest technical report demonstrating how to reduce language model parameters by 77% while maintaining performance.
The secret? Grouped pointwise convolutions. Yes. We brought a method from computer vision to the transformers arena.
π Key Findings:
β’ 77% parameter reduction.
β’ Maintained model capabilities.
β’ Improved generalization.
Paper: https://www.researchgate.net/publication/388835829_SAVING_77_OF_THE_PARAMETERS_IN_LARGE_LANGUAGE_MODELS_TECHNICAL_REPORT
Code: https://github.com/joaopauloschuler/less-parameters-llm
Thrilled to share the latest technical report demonstrating how to reduce language model parameters by 77% while maintaining performance.
The secret? Grouped pointwise convolutions. Yes. We brought a method from computer vision to the transformers arena.
π Key Findings:
β’ 77% parameter reduction.
β’ Maintained model capabilities.
β’ Improved generalization.
Paper: https://www.researchgate.net/publication/388835829_SAVING_77_OF_THE_PARAMETERS_IN_LARGE_LANGUAGE_MODELS_TECHNICAL_REPORT
Code: https://github.com/joaopauloschuler/less-parameters-llm
- 2 replies
liked
3
models
9 days ago
reacted to
MonsterMMORPG's
post with π₯
9 days ago
Post
2661
RTX 5090 Tested Against FLUX DEV, SD 3.5 Large, SD 3.5 Medium, SDXL, SD 1.5 with AMD 9950X CPU and RTX 5090 compared against RTX 3090 TI in all benchmarks. Moreover, compared FP8 vs FP16 and changing prompt impact as well
Video Link : https://youtu.be/jHlGzaDLkto
In this video I have intensively compared RTX 5090 speed on FLUX DEV, FLUX Fill, SD 3.5 Large, SD 3.5 Medium, Stable Diffusion XL (SDXL) and Stable Diffusion 1.5 (SD 1.5) models. For each benchmark, I have compared RTX 5090 against RTX 3090 TI so we see the speed improvement. Moreover, I have tested FP8 vs 16-bit precision for FLUX and SD 3.5 Large and SD 3.5 Medium models. Furthermore, I have tested the speed impact of changing prompt on FLUX DEV model since one of the follower had requested. Full specs of the system provided below.
I have used SwarmUI with ComfyUI backend so these benchmarks are literally done on ComfyUI you can think as. Currently no other interface / UI supporting RTX 5000 series as far as i know.
Video Link : https://youtu.be/jHlGzaDLkto
πAutomatic Installer and Model Downloader RTX 5000 Series Support ‡οΈ
βΆοΈ https://www.patreon.com/posts/installer-and-downloader-rtx5000-series-support-114517862
πManually Install RTX 5000 Series Support ‡οΈ
βΆοΈ https://github.com/comfyanonymous/ComfyUI/discussions/6643
πSECourses 10000+ Members Discord ‡οΈ
βΆοΈ https://discord.com/servers/software-engineering-courses-secourses-772774097734074388
πSECourses Amazing Generative AI GitHub ‡οΈ
βΆοΈ https://github.com/FurkanGozukara/Stable-Diffusion
πSECourses AI APPs Index ‡οΈ
βΆοΈ https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Patreon-Posts-Index.md
πGPU Specs and the used Machine Tutorial ‡οΈ
βΆοΈ https://youtu.be/uV3oqdILOmA
πRTX 5090 Benchmarking Video Series Playlist ‡οΈ
βΆοΈ https://www.youtube.com/playlist?list=PL_pbwdIyffslNd9aLizjQtHVHAMA6tpfT
Video has full chapters so please look at the video description
Video Link : https://youtu.be/jHlGzaDLkto
In this video I have intensively compared RTX 5090 speed on FLUX DEV, FLUX Fill, SD 3.5 Large, SD 3.5 Medium, Stable Diffusion XL (SDXL) and Stable Diffusion 1.5 (SD 1.5) models. For each benchmark, I have compared RTX 5090 against RTX 3090 TI so we see the speed improvement. Moreover, I have tested FP8 vs 16-bit precision for FLUX and SD 3.5 Large and SD 3.5 Medium models. Furthermore, I have tested the speed impact of changing prompt on FLUX DEV model since one of the follower had requested. Full specs of the system provided below.
I have used SwarmUI with ComfyUI backend so these benchmarks are literally done on ComfyUI you can think as. Currently no other interface / UI supporting RTX 5000 series as far as i know.
Video Link : https://youtu.be/jHlGzaDLkto
πAutomatic Installer and Model Downloader RTX 5000 Series Support ‡οΈ
βΆοΈ https://www.patreon.com/posts/installer-and-downloader-rtx5000-series-support-114517862
πManually Install RTX 5000 Series Support ‡οΈ
βΆοΈ https://github.com/comfyanonymous/ComfyUI/discussions/6643
πSECourses 10000+ Members Discord ‡οΈ
βΆοΈ https://discord.com/servers/software-engineering-courses-secourses-772774097734074388
πSECourses Amazing Generative AI GitHub ‡οΈ
βΆοΈ https://github.com/FurkanGozukara/Stable-Diffusion
πSECourses AI APPs Index ‡οΈ
βΆοΈ https://github.com/FurkanGozukara/Stable-Diffusion/blob/main/Patreon-Posts-Index.md
πGPU Specs and the used Machine Tutorial ‡οΈ
βΆοΈ https://youtu.be/uV3oqdILOmA
πRTX 5090 Benchmarking Video Series Playlist ‡οΈ
βΆοΈ https://www.youtube.com/playlist?list=PL_pbwdIyffslNd9aLizjQtHVHAMA6tpfT
Video has full chapters so please look at the video description
- 4 replies
liked
a
dataset
11 days ago
liked
2
models
11 days ago
liked
2
datasets
11 days ago