@not-lain This is great! Thanks for offering this intro session for those new to the HF community.
atayloraerospace PRO
Taylor658
AI & ML interests
Computer Vision π | Multimodal Gen AI π€| AI in Healthcare π©Ί | AI in Aerospace π
Organizations
Taylor658's activity
posted
an
update
4 days ago
Post
1143
Cohere for AI, Argilla, and Hugging Face are collaborating on an Open Science Project to enhance multilingual model evaluations. The project focuses on the widely-used MMLU dataset, which spans 57 subjects like mathematics, computer science, and law. However, existing translations often miss linguistic and cultural nuances, thus embedding biases. π€
To address this, they have annotated a subset of the MMLU test set and are inviting global perspectives to review prompts, highlighting cultural specifics and required knowledge. They have mentioned that insights will help shape future multilingual model evaluations, ensuring they are more inclusive and accurate. πΊοΈ π π
βΆοΈ To get started go to: CohereForAI/MMLU-evaluation
π They also have an Aya Discord server for collaboration with other participants: https://discord.gg/9gVhdfnQMN
To address this, they have annotated a subset of the MMLU test set and are inviting global perspectives to review prompts, highlighting cultural specifics and required knowledge. They have mentioned that insights will help shape future multilingual model evaluations, ensuring they are more inclusive and accurate. πΊοΈ π π
βΆοΈ To get started go to: CohereForAI/MMLU-evaluation
π They also have an Aya Discord server for collaboration with other participants: https://discord.gg/9gVhdfnQMN
posted
an
update
5 days ago
Post
1258
The Hugging Face Computer Vision community will have the first in a series of online hangouts/study groups this Saturday June 1st at 10:00 am EDT.π
Join us on the Hugging Face Discord channel for the Hangout!
https://discord.gg/hugging-face-879548962464493619?event=1243129304863215656 π€
Join us on the Hugging Face Discord channel for the Hangout!
https://discord.gg/hugging-face-879548962464493619?event=1243129304863215656 π€
posted
an
update
8 days ago
Post
1033
Researchers from Anthropic managed to extract millions of interpretable features from their Claude 3 Sonnet model, making it easier to identify and understand specific behaviors and patterns within the modelβ.
This advance in understanding closed source AI models could make them safer by showing how specific features relate to concepts and affect the modelβs behavior.
Read the Article: https://www.anthropic.com/research/mapping-mind-language-model?utm_source=substack&utm_medium=email
Read The Paper: https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html
This advance in understanding closed source AI models could make them safer by showing how specific features relate to concepts and affect the modelβs behavior.
Read the Article: https://www.anthropic.com/research/mapping-mind-language-model?utm_source=substack&utm_medium=email
Read The Paper: https://transformer-circuits.pub/2024/scaling-monosemanticity/index.html
replied to
their
post
9 days ago
You are welcome Omar
posted
an
update
10 days ago
Post
1162
The Google Deep Mind Team just released a new technical report on Gemini 1.5 Pro and Gemini 1.5 Flash.
in addition to architecture, benchmark and evaluation details, the report also provides a few real world use cases for the models such as professional task optimization and translation of lesser-known languages.
You can check out the full report here: https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf?utm_source=substack&utm_medium=email
in addition to architecture, benchmark and evaluation details, the report also provides a few real world use cases for the models such as professional task optimization and translation of lesser-known languages.
You can check out the full report here: https://storage.googleapis.com/deepmind-media/gemini/gemini_v1_5_report.pdf?utm_source=substack&utm_medium=email
posted
an
update
12 days ago
Post
1772
A new paper, "Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning," was just published. The approach improves VLMs' decision-making abilities in goal-directed tasks.
This is accomplished with Chain-of-thought (COT) reasoning, which seriously enhances performance. Removing COT reasoning, however, drops effectiveness, highlighting its crucial role.
Check out the paper here: https://arxiv.org/abs/2405.10292
This is accomplished with Chain-of-thought (COT) reasoning, which seriously enhances performance. Removing COT reasoning, however, drops effectiveness, highlighting its crucial role.
Check out the paper here: https://arxiv.org/abs/2405.10292
Yes some potential multi input or multi source coded related tasks could be - executing shell commands directly from a script, deserialization of untrusted data, or parsing xml data for example. CWE-611 and CWE-502 might already cover a couple of these coding scenarios though...
posted
an
update
17 days ago
Post
1684
Another excellent course has launched on Hugging Face Learn https://huggingface.co/learn
HF Developer Advocate Dylan Ebert has officially launched the ML for 3D Course! π€
Check it out @ https://huggingface.co/learn/ml-for-3d-course/unit0/introduction
YT Channel: https://www.youtube.com/@IndividualKex
GitHub: https://github.com/huggingface/ml-for-3d-course
HF Developer Advocate Dylan Ebert has officially launched the ML for 3D Course! π€
Check it out @ https://huggingface.co/learn/ml-for-3d-course/unit0/introduction
YT Channel: https://www.youtube.com/@IndividualKex
GitHub: https://github.com/huggingface/ml-for-3d-course
Thanks for posting results for gpt-4o so fast!
You will have to post the latest Gemini model results tomorrow after I/O announcements. :-)
Since we are squarely in the age of multimodal models I am curious if any of the 76 standard scripts run for vulnerability remediation in "static-analysis-eval" demonstrate multimodal vulnerabilities?
posted
an
update
21 days ago
Post
1102
Red Hat and IBM have announced InstructLab, an open-source project for LLM contributions. InstructLab offers a model-agnostic approach for the community to contribute "skills" and or "knowledge" to LLMs via a CLI and tuning backend.
This community-driven approach to GenAI model development is novel to say the least. It will be interesting to see how effective it is in the long run, especially on models beyond the initial Granite and Merlinite familes.
Can check out Git Hub here: https://github.com/instructlab
Read the LAB Paper: https://arxiv.org/abs/2403.01081
View Model Builds: https://huggingface.co/instructlab
This community-driven approach to GenAI model development is novel to say the least. It will be interesting to see how effective it is in the long run, especially on models beyond the initial Granite and Merlinite familes.
Can check out Git Hub here: https://github.com/instructlab
Read the LAB Paper: https://arxiv.org/abs/2403.01081
View Model Builds: https://huggingface.co/instructlab
replied to
mattmdjaga's
post
22 days ago
Thanks for posting about the course!
posted
an
update
22 days ago
Post
1102
π€The first submissions from the Community Hugging Face Computer Vision Course (https://huggingface.co/learn/computer-vision-course/unit0/welcome/welcome) are being posted up on HF Spaces!π€
OmAlve/Swin-Transformer-Foods101
Rageshhf/medi-classifier
It is amazing that the first group of students has completed the course and in record time!
Will look forward to seeing more submissions from the course soon.
A nice swag item that students get when they complete the course and make their submission is this cool Hugging Face Certificate of Completion. (Its suitable for framing) π€
π
OmAlve/Swin-Transformer-Foods101
Rageshhf/medi-classifier
It is amazing that the first group of students has completed the course and in record time!
Will look forward to seeing more submissions from the course soon.
A nice swag item that students get when they complete the course and make their submission is this cool Hugging Face Certificate of Completion. (Its suitable for framing) π€
π
posted
an
update
30 days ago
Post
2168
The Open Medical-LLM Leaderboard is now up on HF Spaces. π€
openlifescienceai/open_medical_llm_leaderboard
It will be interesting to add the results of the just announced Med-Gemini model to the Leaderboard to see how it compares and if its stated 91.1% MedQA benchmark is accurate.
Capabilities of Gemini Models in Medicine (2404.18416)
openlifescienceai/open_medical_llm_leaderboard
It will be interesting to add the results of the just announced Med-Gemini model to the Leaderboard to see how it compares and if its stated 91.1% MedQA benchmark is accurate.
Capabilities of Gemini Models in Medicine (2404.18416)