alexsherstinsky/unsloth_llava-v1.6-mistral-7b-hf-bnb-4bit-llm-finetuned-llava-instruct-mix-vsft-mini-notmerged
Updated
Alex Sherstinsky
alexsherstinsky
AI & ML interests
None yet
Recent Activity
updated
a model
7 days ago
alexsherstinsky/unsloth_pixtral-12B-2409-llm-finetuned-llava-instruct-mix-vsft-mini-notmerged
Organizations
None yet
alexsherstinsky's activity
updated
a
model
6 days ago
updated
a
model
7 days ago
liked
a
model
3 months ago
updated
3
models
5 months ago
Reacted to
dvilasuero's
post with ❤️🤗🚀🔥
6 months ago
Post
7985
Today is a huge day in Argilla’s history. We couldn’t be more excited to share this with the community: we’re joining Hugging Face!
We’re embracing a larger mission, becoming part of a brilliant and kind team and a shared vision about the future of AI.
Over the past year, we’ve been collaborating with Hugging Face on countless projects: launching partner of Docker Spaces, empowering the community to clean Alpaca translations into Spanish and other languages, launching argilla/notus-7b-v1 building on Zephyr’s learnings, the Data is Better Together initiative with hundreds of community contributors, or releasing argilla/OpenHermesPreferences, one of the largest open preference tuning datasets
After more than 2,000 Slack messages and over 60 people collaborating for over a year, it already felt like we were part of the same team, pushing in the same direction. After a week of the smoothest transition you can imagine, we’re now the same team.
To those of you who’ve been following us, this won’t be a huge surprise, but it will be a big deal in the coming months. This acquisition means we’ll double down on empowering the community to build and collaborate on high quality datasets, we’ll bring full support for multimodal datasets, and we’ll be in a better place to collaborate with the Open Source AI community. For enterprises, this means that the Enterprise Hub will unlock highly requested features like single sign-on and integration with Inference Endpoints.
As a founder, I am proud of the Argilla team. We're now part of something bigger and a larger team but with the same values, culture, and goals. Grateful to have shared this journey with my beloved co-founders Paco and Amélie.
Finally, huge thanks to the Chief Llama Officer @osanseviero for sparking this and being such a great partner during the acquisition process.
Would love to answer any questions you have so feel free to add them below!
We’re embracing a larger mission, becoming part of a brilliant and kind team and a shared vision about the future of AI.
Over the past year, we’ve been collaborating with Hugging Face on countless projects: launching partner of Docker Spaces, empowering the community to clean Alpaca translations into Spanish and other languages, launching argilla/notus-7b-v1 building on Zephyr’s learnings, the Data is Better Together initiative with hundreds of community contributors, or releasing argilla/OpenHermesPreferences, one of the largest open preference tuning datasets
After more than 2,000 Slack messages and over 60 people collaborating for over a year, it already felt like we were part of the same team, pushing in the same direction. After a week of the smoothest transition you can imagine, we’re now the same team.
To those of you who’ve been following us, this won’t be a huge surprise, but it will be a big deal in the coming months. This acquisition means we’ll double down on empowering the community to build and collaborate on high quality datasets, we’ll bring full support for multimodal datasets, and we’ll be in a better place to collaborate with the Open Source AI community. For enterprises, this means that the Enterprise Hub will unlock highly requested features like single sign-on and integration with Inference Endpoints.
As a founder, I am proud of the Argilla team. We're now part of something bigger and a larger team but with the same values, culture, and goals. Grateful to have shared this journey with my beloved co-founders Paco and Amélie.
Finally, huge thanks to the Chief Llama Officer @osanseviero for sparking this and being such a great partner during the acquisition process.
Would love to answer any questions you have so feel free to add them below!
- 28 replies
replied to
singhsidhukuldeep's
post
6 months ago
@elsatch Thank you for tagging me in this conversation! I think that while the approach with LoRA adapters would (in my opinion) be relying on a different technique, the results could indeed be favorable. Here are some recent papers that point to high effectiveness of LoRA as a specific PEFT method on a variety of examples and application domains:
- https://www.linkedin.com/posts/josh-longenecker-5a6902226_peft-welcomes-new-merging-methods-activity-7166246108854210560--BCB/?utm_source=share&utm_medium=member_desktop
- https://www.linkedin.com/posts/pieromolino_opensource-ai-llm-activity-7199154086888284160-jQPC?utm_source=share&utm_medium=member_desktop
- https://www.linkedin.com/posts/claudio-mastronardo-aa44b7154_llm-generativeai-nlp-activity-7194961942623449088--6nN?utm_source=share&utm_medium=member_desktop
Happy to discuss! Thanks again!
updated
4
models
7 months ago
alexsherstinsky/predibase-plus-gretel-ai-text-to-sql-phi-3-mini-4k-instruct-no-json
Updated
•
1
alexsherstinsky/predibase-plus-gretel-ai-text-to-sql-mistral-7b-instruct-v0-2-no-json
Updated
•
4
alexsherstinsky/predibase-plus-gretel-ai-text-to-sql-llama-3-8b-instruct-no-json
Updated
•
2
alexsherstinsky/predibase-plus-gretel-ai-text-to-sql-phi-3-no-json
Updated
•
5
authored
a
paper
7 months ago
updated
3
models
8 months ago
alexsherstinsky/mistral-7b-v0.1-based-finetuned-using-ludwig-with-bitext-accounts-A100-4bit-notmerged
Updated
alexsherstinsky/mistral-7b-v0.1-based-finetuned-using-ludwig-with-bitext-orders-A100-4bit-notmerged
Updated
•
2
alexsherstinsky/mistral-7b-v0.1-based-finetuned-using-ludwig-with-bitext-payments-A100-4bit-notmerged
Updated
updated
a
model
9 months ago