BEE-spoke-data/google_wellformed_query-hf
Viewer
ā¢
Updated
ā¢
25.1k
ā¢
7
BEEspoke Data
community
AI & ML interests
'an LLM is only as good as the dataset it was trained on' - Sun Tzu
Recent Activity
View all activity
BEE-spoke-data's activity
pszemrajĀ
updated
a
dataset
6 days ago
pszemrajĀ
updated
a
dataset
17 days ago
pszemrajĀ
updated
a
Space
20 days ago
pszemrajĀ
updated
2
datasets
29 days ago
pszemrajĀ
updated
a
model
about 2 months ago
Post
3886
nanoLLaVA-1.5 is here! Same size (1B), better performance š„š„š„
And it is much more powerful than v1.0
Try it out now on HF Spaces: qnguyen3/nanoLLaVA
Model: qnguyen3/nanoLLaVA-1.5
And it is much more powerful than v1.0
Try it out now on HF Spaces: qnguyen3/nanoLLaVA
Model: qnguyen3/nanoLLaVA-1.5
- 3 replies
huu-ontocordĀ
authored
a
paper
8 months ago
Post
5306
š Introducing nanoLLaVA, a powerful multimodal AI model that packs the capabilities of a 1B parameter vision language model into just 5GB of VRAM. š This makes it an ideal choice for edge devices, bringing cutting-edge visual understanding and generation to your devices like never before. š±š»
Model: qnguyen3/nanoLLaVA š
Spaces: qnguyen3/nanoLLaVA (thanks to @merve )
Under the hood, nanoLLaVA is based on the powerful vilm/Quyen-SE-v0.1 (my Qwen1.5-0.5B finetune) and Google's impressive google/siglip-so400m-patch14-384. š§ The model is trained using a data-centric approach to ensure optimal performance. š
In the spirit of transparency and collaboration, all code and model weights are open-sourced under the Apache 2.0 license. š¤
Model: qnguyen3/nanoLLaVA š
Spaces: qnguyen3/nanoLLaVA (thanks to @merve )
Under the hood, nanoLLaVA is based on the powerful vilm/Quyen-SE-v0.1 (my Qwen1.5-0.5B finetune) and Google's impressive google/siglip-so400m-patch14-384. š§ The model is trained using a data-centric approach to ensure optimal performance. š
In the spirit of transparency and collaboration, all code and model weights are open-sourced under the Apache 2.0 license. š¤
- 1 reply
tanmaylaudĀ
authored
3
papers
9 months ago
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Paper
ā¢
2404.00399
ā¢
Published
ā¢
41
ClimaBench: A Benchmark Dataset For Climate Change Text Understanding in English
Paper
ā¢
2301.04253
ā¢
Published
ā¢
1
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Paper
ā¢
2211.05100
ā¢
Published
ā¢
27
kenhktsuiĀ
authored
a
paper
9 months ago
huu-ontocordĀ
posted
an
update
9 months ago
Post
1641
We would like to announce our Aurora-M multilingual models which is based on Starcoderplus.
Twitter: https://twitter.com/ontocord/status/1772778544051155029
LinkedIn: https://www.linkedin.com/feed/update/urn:li:activity:7178521998845759488/
Blog post: https://huggingface.co/blog/mayank-mishra/aurora
Arxiv: Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order (2404.00399)
Current LLMs are very susceptible to generating toxic, harmful and even dangerous content. They can also generate outputs with gender or racial biases. The Biden-Harris Executive Order https://www.federalregister.gov/documents/2023/11/01/2023-24283/safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence) sets forth guidelines on what is considered a safe AI system.
Following up on these guidelines, we present the world's first open source Biden-Harris Executive Order Red teamed Multilingual Language Model: Aurora-M. Inspired by BigScience, the model is trained on 5 languages: English, Hindi, Japanese, Vietnamese and Finnish.
* Red teamed model: aurora-m/aurora-m-biden-harris-redteamed tuned according to the order mentioned above)
* Base model: aurora-m/aurora-m-base (not safety tuned)
* Instruct model: aurora-m/aurora-m-instruct (not safety tuned)
@mayank-mishra @cabbage972 @sted97 @Xa9aX @Taishi-N324 @Muennighoff @vumichien @prateeky2806 @felfri @spyysalo and many many others!
Twitter: https://twitter.com/ontocord/status/1772778544051155029
LinkedIn: https://www.linkedin.com/feed/update/urn:li:activity:7178521998845759488/
Blog post: https://huggingface.co/blog/mayank-mishra/aurora
Arxiv: Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order (2404.00399)
Current LLMs are very susceptible to generating toxic, harmful and even dangerous content. They can also generate outputs with gender or racial biases. The Biden-Harris Executive Order https://www.federalregister.gov/documents/2023/11/01/2023-24283/safe-secure-and-trustworthy-development-and-use-of-artificial-intelligence) sets forth guidelines on what is considered a safe AI system.
Following up on these guidelines, we present the world's first open source Biden-Harris Executive Order Red teamed Multilingual Language Model: Aurora-M. Inspired by BigScience, the model is trained on 5 languages: English, Hindi, Japanese, Vietnamese and Finnish.
* Red teamed model: aurora-m/aurora-m-biden-harris-redteamed tuned according to the order mentioned above)
* Base model: aurora-m/aurora-m-base (not safety tuned)
* Instruct model: aurora-m/aurora-m-instruct (not safety tuned)
@mayank-mishra @cabbage972 @sted97 @Xa9aX @Taishi-N324 @Muennighoff @vumichien @prateeky2806 @felfri @spyysalo and many many others!
huu-ontocordĀ
authored
3
papers
9 months ago
OpenAssistant Conversations -- Democratizing Large Language Model Alignment
Paper
ā¢
2304.07327
ā¢
Published
ā¢
5
Data Governance in the Age of Large-Scale Data-Driven Language Technology
Paper
ā¢
2206.03216
ā¢
Published
Aurora-M: The First Open Source Multilingual Language Model Red-teamed according to the U.S. Executive Order
Paper
ā¢
2404.00399
ā¢
Published
ā¢
41
qnguyen3Ā
authored
a
paper
about 1 year ago
pszemrajĀ
updated
2
models
about 1 year ago