rilixai/20260401_purchase_order_sft-20260331_sft_dataset_fixed
Viewer • Updated • 4.98k • 29
AI & ML interests
None defined yet.
EllaHC
updated a
dataset 9 days ago
EllaHC
published a
dataset 9 days ago
EllaHC
updated a
dataset 9 days ago
EllaHC
published a
dataset 9 days ago
EllaHC
updated a
dataset 9 days ago
EllaHC
published a
dataset 9 days ago
EllaHC
updated a
dataset 9 days ago
EllaHC
published a
dataset 9 days ago
EllaHC
updated a
dataset 11 days ago
EllaHC
published a
dataset 11 days ago
VictorSanh
posted an update almost 2 years ago
Post
3249
💬🔥Releasing idefics2-8b-chatty, the chat-optimized version of Idefics2!
It is a very efficient (8B parameters) state-of-the-art VLM, has been red-teamed, and comes with a few surprises:
- 📖Paper dissecting a lot of the experimental insights we learned building Idefics2:
- 🏎️TGI integration for blazing-fast inference (you can already run it locally with < 24GB GPU memory)
- 🏆 Ranking 2nd in its category (< 10B, open weights) in the awesome Open VLM Leaderboard, and now appearing in the incredible Vision Arena
Ressources:
⏯️Playground: HuggingFaceM4/idefics2_playground
📖Paper: What matters when building vision-language models? (2405.02246)
🏋️♂️Model and red-teaming analysis: HuggingFaceM4/idefics2-8b-chatty
👀Ressources to get started: HuggingFaceM4/idefics2-8b-chatty
🏆Open VLM Leaderboard: opencompass/open_vlm_leaderboard
🏟️Vision arena: WildVision/vision-arena
It is a very efficient (8B parameters) state-of-the-art VLM, has been red-teamed, and comes with a few surprises:
- 📖Paper dissecting a lot of the experimental insights we learned building Idefics2:
- 🏎️TGI integration for blazing-fast inference (you can already run it locally with < 24GB GPU memory)
- 🏆 Ranking 2nd in its category (< 10B, open weights) in the awesome Open VLM Leaderboard, and now appearing in the incredible Vision Arena
Ressources:
⏯️Playground: HuggingFaceM4/idefics2_playground
📖Paper: What matters when building vision-language models? (2405.02246)
🏋️♂️Model and red-teaming analysis: HuggingFaceM4/idefics2-8b-chatty
👀Ressources to get started: HuggingFaceM4/idefics2-8b-chatty
🏆Open VLM Leaderboard: opencompass/open_vlm_leaderboard
🏟️Vision arena: WildVision/vision-arena
- 1 reply
VictorSanh
authored a
paper almost 2 years ago
VictorSanh
posted an update almost 2 years ago
Post
2885
Glad to see Idefics2 making its way into the awesome OpenVLM Leaderboard which ranks VLMs. 🏆
2nd in its category (<10B parameters and open weights)!
While InternLM-XComposer2 uses proprietary data, Idefics2 is built solely using openly available data.
Leaderboard: opencompass/open_vlm_leaderboard
Model: HuggingFaceM4/idefics2-8b
2nd in its category (<10B parameters and open weights)!
While InternLM-XComposer2 uses proprietary data, Idefics2 is built solely using openly available data.
Leaderboard: opencompass/open_vlm_leaderboard
Model: HuggingFaceM4/idefics2-8b
- 9 replies
VictorSanh
authored 5
papers almost 2 years ago
TransferTransfo: A Transfer Learning Approach for Neural Network Based Conversational Agents
Paper • 1901.08149 • Published • 3
Movement Pruning: Adaptive Sparsity by Fine-Tuning
Paper • 2005.07683 • Published
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts
Paper • 2202.01279 • Published
Learning from others' mistakes: Avoiding dataset biases without modeling them
Paper • 2012.01300 • Published
A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks
Paper • 1811.06031 • Published
VictorSanh
posted an update almost 2 years ago
Post
2545
Can't wait to see multimodal LLama 3!
We released a resource that might come in handy: The Cauldron 🍯
The Cauldron is a massive manually-curated collection of 50 vision-language sets for instruction fine-tuning. 3.6M images, 30.3M query/answer pairs.
It covers a large variety of downstream uses: visual question answering on natural images, OCR, document/charts/figures/tables understanding, textbooks/academic question, reasoning, captioning, spotting differences between 2 images, and screenshot-to-code.
HuggingFaceM4/the_cauldron
We released a resource that might come in handy: The Cauldron 🍯
The Cauldron is a massive manually-curated collection of 50 vision-language sets for instruction fine-tuning. 3.6M images, 30.3M query/answer pairs.
It covers a large variety of downstream uses: visual question answering on natural images, OCR, document/charts/figures/tables understanding, textbooks/academic question, reasoning, captioning, spotting differences between 2 images, and screenshot-to-code.
HuggingFaceM4/the_cauldron
- 1 reply
VictorSanh
posted an update almost 2 years ago
Post
2771
New open multimodal model in town: Idefics2!
💪 Strong 8B-parameters model: often on par with open 30B counterparts.
🔓Open license: Apache 2.0.
🚀 Strong improvement over Idefics1: +12 points on VQAv2, +30 points on TextVQA while having 10x fewer parameters.
📚 Better data: boosting OCR capabilities with 6TB of documents to transcribe, and improving QA capabilities on charts/figures/diagrams.
🕵️♀️ Transparent training data: inspect and build upon all the data (10s of TB of data) we trained on.
🔲 More natural image processing: Incorporating strategies to treat images in their native resolution and native aspect ratio.
📸 High-resolution images: image resolutions up to 980 x 980 and integrating strategies that allow to trade computational efficiency for performance.
😎 2 checkpoints: Releasing both base checkpoint and instruction fine-tuned checkpoint. Chat version to come.
Ressources: HuggingFaceM4/idefics2-661d1971b7c50831dd3ce0fe
Blogpost: https://huggingface.co/blog/idefics2
💪 Strong 8B-parameters model: often on par with open 30B counterparts.
🔓Open license: Apache 2.0.
🚀 Strong improvement over Idefics1: +12 points on VQAv2, +30 points on TextVQA while having 10x fewer parameters.
📚 Better data: boosting OCR capabilities with 6TB of documents to transcribe, and improving QA capabilities on charts/figures/diagrams.
🕵️♀️ Transparent training data: inspect and build upon all the data (10s of TB of data) we trained on.
🔲 More natural image processing: Incorporating strategies to treat images in their native resolution and native aspect ratio.
📸 High-resolution images: image resolutions up to 980 x 980 and integrating strategies that allow to trade computational efficiency for performance.
😎 2 checkpoints: Releasing both base checkpoint and instruction fine-tuned checkpoint. Chat version to come.
Ressources: HuggingFaceM4/idefics2-661d1971b7c50831dd3ce0fe
Blogpost: https://huggingface.co/blog/idefics2