Quentin Gallouédec's picture

Quentin Gallouédec

qgallouedec

·

https://gallouedec.com

AI & ML interests

None yet

Recent Activity

updated a dataset about 12 hours ago

qgallouedec/trl-metrics

updated a dataset 1 day ago

trl-lib/documentation-images

replied to merve's post 5 days ago

Oof, what a week! 🥵 So many things have happened, let's recap! https://huggingface.co/collections/merve/jan-24-releases-6793d610774073328eac67a9 Multimodal 💬 - We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG 💗 - UI-TARS are new models by ByteDance to unlock agentic GUI control 🤯 in 2B, 7B and 72B - Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B - MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context - Dataset: Yale released a new benchmark called MMVU - Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark LLMs 📖 - DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! 🤯 - Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B - NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!) Audio 🗣️ - Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B - TangoFlux is a new audio generation model trained from scratch and aligned with CRPO Image/Video/3D Generation ⏯️ - Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux - tencent released Hunyuan3D-2, new 3D asset generation from images

View all activity

Articles

Visualize and understand GPU memory in PyTorch

Preference Optimization for Vision Language Models

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

Organizations

qgallouedec's activity

New activity in HuggingFaceH4/blogpost-scaling-test-time-compute about 1 month ago

Use HF papers

#2 opened about 1 month ago by

Update app/src/index.html

#1 opened about 1 month ago by

New activity in science/README 2 months ago

Update README.md

#1 opened 2 months ago by

New activity in pdf2dataset/pdf2dataset 2 months ago

Space in Runtime error

#1 opened 3 months ago by

davidberenstein1957

New activity in trl-lib/prm800k 2 months ago

Librarian Bot: Add language metadata for dataset

#2 opened 2 months ago by

New activity in trl-internal-testing/tldr-preference-sft-trl-style 5 months ago

Revert changes

#3 opened 5 months ago by

New activity in trl-internal-testing/sentiment-trl-style 6 months ago

Librarian Bot: Add language metadata for dataset

#3 opened 7 months ago by

New activity in qgallouedec/suap_essentials 6 months ago

Librarian Bot: Add language metadata for dataset

#2 opened 7 months ago by

New activity in trl-internal-testing/descriptiveness-trl-style 6 months ago

Librarian Bot: Add language metadata for dataset

#1 opened 7 months ago by

New activity in pdf2dataset/9dd4aa46827d0967f4dbd7cce208a5f7 6 months ago

Update README.md

#1 opened 6 months ago by

New activity in HuggingFaceH4/compare_idefics-8b-dpo 7 months ago

Upload howl.jpg

#4 opened 7 months ago by

Update app.py

#3 opened 7 months ago by

Update app.py

#1 opened 7 months ago by

Upload bee.jpg

#2 opened 7 months ago by

New activity in huggingface/documentation-images 7 months ago

vdpo-image

#347 opened 7 months ago by

vdpo blog post

#346 opened 7 months ago by

dpo_vlm

#344 opened 7 months ago by

New activity in jat-project/jat-dataset 7 months ago

[WARNING for everyone] image_observation is NOT IMAGE, it is frame-stacked 4 grayscale images

#3 opened 8 months ago by

New activity in jat-project/jat-dataset-tokenized 7 months ago

[bot] Conversion to Parquet

#1 opened about 1 year ago by

parquet-converter

What is the folder with triple underscores?

#2 opened 8 months ago by