Semanlink - Favoris ; Machine learning AND Cannibalizing LLMs

Printer friendly

Search Tag:

Search Doc:

Preferences...

Tag Cloud

Alpaca - Arxiv Doc - Blog - Cannibalizing LLMs - ChatGPT - Chris Olah - Dataset quality - Fine-tuning - François Chollet - GitHub Pages - GitHub project - Good - Google - Google AI Blog - Instruction tuning - Knowledge Graphs - Language Model - LLaMA - LLM - Machine learning - ML/NLP blog - MongoDB - Neural networks - News - NLP - NLP@Google - NLP@Meta - OpenAI - Open Source - Ranking (information retrieval) - Searching by description - Sylvain Gugger - Tutorial - Tweet -

Favoris ; Machine learning AND Cannibalizing LLMs

Common descendants

29 Documents

Improving Search Ranking with Few-Shot Prompting of LLMs | Vespa Blog

Tags:

2023-07-07 About

[2305.12517] Retrieving Texts based on Abstract Descriptions

Tags:

2023-06-15 About

Aran Komatsuzaki sur Twitter : "The False Promise of Imitating Proprietary LLMs..."

Tags:

2023-06-03 About

How to use Alpaca-LoRA to fine-tune a model like ChatGPT

Tags:

2023-05-26 About

@yoavgo sur Twitter : "searching by description can be very useful, but current embedding models will give you texts that are *similar* to the description, rather than texts that *adhere to it*..."

Tags:

2023-05-24 About

Build a ChatGPT with your Private Data using LlamaIndex and MongoDB | by Jerry Liu | LlamaIndex Blog | May, 2023 | Medium

Tags:

2023-05-21 About

Google "We Have No Moat, And Neither Does OpenAI"

Tags:

> low-cost public involvement was enabled
by a vastly cheaper mechanism for fine tuning called low
rank adaptation ()[LoRA](tag:lora)

> **Part of what makes LoRA so effective is that ... it’s stackable.**
>
> By contrast, training giant models from scratch not only
throws away the pretraining, but also any iterative
improvements that have been made on top.

> LoRA updates are very cheap to produce (~$100) for the
most popular model sizes.

> Many of these projects are saving time by training on
small, highly curated datasets...
> These
datasets are built using synthetic methods (e.g. filtering
the best responses from an existing model) and
scavenging from other projects

> Directly Competing With Open Source
Is a Losing Proposition

> Paradoxically, the one clear winner in all of this is Meta.
Because the leaked model was theirs ([LLaMA](tag:llama)), they have
effectively garnered an entire planet's worth of free labor.
Since most open source innovation is happening on top of
their architecture, there is nothing stopping them from
directly incorporating it into their products.

2023-05-04 About

Daniel Vila Suero sur Twitter : "Data quality is key for LLMs, but we're building Open Source LLMs with data of "unknown" quality... Introducing Alpaca GarbageCollector..."

Tags:

2023-04-05 About

Alpaca Finetuning of Llama on a 24G Consumer GPU

Tags:

2023-03-27 About

tloen/alpaca-lora: Instruct-tune LLaMA on consumer hardware

Tags:

2023-03-22 About

LLM Zoo at Home: LLaMA & Alpaca | bergis universe of software, hardware and ideas

Tags:

2023-03-20 About

Guiding Frozen Language Models with Learned Soft Prompts – Google AI Blog

Tags:

2023-02-14 About

The Flan Collection: Advancing open source methods for instruction tuning – Google AI Blog

Tags:

2023-02-02 About

Characterizing Emergent Phenomena in Large Language Models – Google AI Blog

Tags:

2023-01-26 About

François Chollet sur Twitter : "I'm pretty optimistic that the LLM reliability / factualness issue can be fixed. The key is to use LLMs as a dialog interface and not as a store of knowledge..."

Tags:

2023-01-24 About

Google AI Blog: Pathways Language Model (PaLM): Scaling to 540 Billion Parameters for Breakthrough Performance

Tags:

2022-04-05 About

Tags:

2021-12-17 About

Google AI Blog: Exploring Transfer Learning with T5: the Text-To-Text Transfer Transformer (2020)

Tags:

2021-10-13 About

elvis sur Twitter : "Today I kept thinking about the machine learning / NLP / deep learning related blog posts (not papers) that have been transformational for me..."

Tags:

2020-12-22 About

NLP Newsletter: The Annotated GPT-2, Understanding self-distillation, Haiku, GANILLA, Sparkwiki, Ethics in NLP, Torchmeta,…

Tags:

2020-02-24 About

Your own blog with GitHub Pages and fast_template (4 part tutorial) · fast.ai

Tags:

2020-01-21 About

Syncing your blog with your PC, and using your word processor · fast.ai

Tags:

2020-01-19 About

Another data science student's blog (Sylvain Gugger)

Tags:

2019-01-03 About

Distill — Latest articles about machine learning

Tags:

2018-09-09 About

Off the convex path

Tags:

2018-09-09 About

Depends on the definition - it's about machine learning, data science and more

Tags:

2018-09-09 About

NLP News | Revue

Tags:

2018-05-29 About

Tags:

2015-10-16 About

Real-Time Topic Modeling of Microblogs

Tags:

2014-04-22 About