ashvanths.bsky.social
Deep Learning Practitioner | Language Lead for Tamil @ HuggingFace | Interested in Continual Learning and Generative Models |
Website : https://ash-01xor.github.io/
X : https://twitter.com/ashvanth_s1
59 posts
57 followers
73 following
Prolific Poster
Conversation Starter
comment in response to
post
Ahh finally a blog post from you , it is quite difficult to maintain a site right like publishing frequent posts
comment in response to
post
Happy new year sebastian !! was waiting for the post
comment in response to
post
which in itself is based on the success of their previous films.
As risks taken decreases due to a formulaic process , so does the excitement and the curiosity.
comment in response to
post
the big names present in the resume is overlooked as a factor of judgement for their talent or in making films where rather than the concept or story , the focus shifts to the kind of artists brought in to play the characters , their star power and influence to bring audience to theaters ...
comment in response to
post
Big thanks to @dvilasuero.hf.co , @nataliaelv.hf.co and team 🙌. Would love to see more people join this effort
comment in response to
post
While these are like the summary of what he considers to be the trends going on right now , interesting to note how it might span out in the future.
Looking forward to building now !
comment in response to
post
- Enterprise Search: Integrating LLMs with search capabilities empowers intelligent assistants to manage vast knowledge bases effectively.
- Assistant Applications: These solutions improve workflows by providing accurate, context-aware information.
comment in response to
post
- Support Customization: Adaptation of models to domain-specific data for optimal performance.
Trend 3: The Convergence of LLMs and Search
Large language models (LLMs) and search are increasingly intertwined, revolutionizing information retrieval:
....
comment in response to
post
Trend 2 : Platform Choice matters
The right platform can determine the success of AI initiatives. Enterprises benefit from platforms that:
- Provide Pretrained Models : Easy access to SOTA models.
- Enable Production Management: Seamless monitoring and scaling in real-world deployments....
comment in response to
post
Democratization: AI tools are increasingly accessible, enabling more people to develop AI without extensive resources.
Generalization Across Tasks: The shift towards universal models capable of performing millions of tasks replaces the need for task-specific models....
comment in response to
post
Trend 1 : AI is Accelerating**
AI development is speeding up, and breaking barriers in scale and accessibility. Key advancements include:
- Data Efficiency: Models require less training data thanks to improved algorithms and pretraining paradigms that leverage foundational knowledge....
comment in response to
post
This would not have been possible without the joint vision of our team. Thanks to each one of them for contributing.
comment in response to
post
An open-source effort at its fullest: open weights, open data, open code.
Hugging Face: huggingface.co/maya-multimo...
Code: github.com/nahidalam/ma...
Thanks to Cohere for AI as well for supporting us.
comment in response to
post
For most lexical based engines , it just works and if your dataset size is lower even more reasons to pursue it. Yes using S-BERT and other fancy methods might seem like good idea but the process is to ensure that you have simple baseline first and then all these fancy methods come up.
comment in response to
post
Congratss Lucas , love how you are doing this FAQ both on X as well as here :)
comment in response to
post
Yes indeed , made a PR already 😀.
comment in response to
post
It is more about understanding the process used to train the model using TRL and other libraries potentially.
Might also write a blog on it , do let me know if you are interested to read on it (might help me get started to work on it :) )
comment in response to
post
Hiiii Zach , hope you are doing fine !
comment in response to
post
Lol saw the leaderboard , someone solved it within 9 seconds . Like someone have an entire pipeline setup and read to download data , send it to LLM and submit it back.
Damn quite a surprise.