ikka (@Shahules786) / X

ikka

1,402 posts

ikka

@Shahules786

Vibing at @vibrantlabsai

San Francisco, CA

Joined January 2017

Pinned
ikka
@Shahules786
Apr 17
We’re building a community of the greatest minds in RL research. This week, we kicked off our first private dinner in SF for handpicked researchers working on autonomously scaling RL environments. Closed-door technical conversations only, no VCs. All people who are betting
23K
ikka
@Shahules786
Jan 15, 2024
The DeepSeek paper has made a significant breakthrough in Mixture of Experts (MoEs) models. 1/n
205K
ikka
@Shahules786
Mar 6, 2024
Officially a YC company 🚀
Y Combinator
@ycombinator
Mar 6, 2024
YC W24's @ragas_io is an open-source evaluation and testing infrastructure for developers to deploy LLM applications with confidence — their model-graded evaluations and testing techniques ensure quality. ycombinator.com/launches/KZO-r… Congrats on the launch, Jitin and @Shahules786!
80K
ikka
@Shahules786
Jan 18, 2024
The RAG vs finetuning work from Microsoft assumes that finetuning can infuse new factual/domain-specific knowledge into LLMs which is not true. Finetuning is not an alternative to RAG. As of now, only something like continual pertaining has proved to add new domain knowledge to
88K
ikka
@Shahules786
Aug 9, 2023
LoRA is not a drop-in replacement for Full Finetuning. Even though it reduces the compute requirements by 3x it comes with certain limitations. The data preparation needed for both is also different. 🔑 - LoRA requires much more data to converge compared to full FT. This can be
245K
ikka
@Shahules786
Jul 25, 2023
Releasing Open-Assistant llama2 13B orca style chat model fine-tuned for up to context length of 8k. We will be releasing more of Llama 2 long context models in the coming weeks! Check out the model huggingface.co/OpenAssistant/… Here's a preview of the generations :
OpenAssistant/llama2-13b-orca-8k-3319 · Hugging Face
From huggingface.co
54K
ikka
@Shahules786
May 18, 2023
FrugalGPT proposes a set of methods to reduce the cost of LLMs in production by up to 98% without comprising performance. So what's the magic? 1/🧵 arxiv.org/pdf/2305.05176…
82K
ikka
@Shahules786
Aug 26, 2023
Overfitting to the public leaderboard is one of the main causes why open-source models struggle when used in real-world use cases. Here’s an example, the data preparation for wizard-coder uses human eval pass@1 scores to decide if to evolve the dataset further or not.
130K
ikka
@Shahules786
Jun 8, 2023
Building Chatbot for your private knowledge base has never been so easy. But improving its performance is still hard and If you can't measure it, you can't improve it. This is where Ragas framework comes in with SOTA evaluation techniques for your RAG pipeline. 🚨 We are
GIF
65K
ikka
@Shahules786
Jan 22, 2024
Contrastive Preference Optimization (CPO), a newly proposed method, outperforms DPO in efficiency and effectiveness for preference optimization. 🔥 (1/n)
36K
ikka
@Shahules786
Feb 8, 2024
We are releasing version 0.1 of Ragas today, the open-source standard for evaluating RAG applications. 🔥 Some highlights of v0.1.0 : ⚡️ Asynchronous and super-fast evaluations. 🥷🏻A stable and improved version of automated synthetic test data generation. 🚀 Automated language
GIF
33K
ikka
@Shahules786
Oct 11, 2023
OpenAI embeddings v/s Flag embeddings on your own data. 🔥 I built a simple notebook showing how to objectively compare different embeddings on one's own data for building RAG pipelines. Learn how to do it docs.ragas.io/en/latest/howt…
GIF
32K
ikka
@Shahules786
Nov 21, 2023
Not the best time to ask for a feature @OpenAI, but I think many can benefit from a search bar to search through conversation history.
13K
ikka
@Shahules786
Oct 16, 2023
Launching our docs today docs.ragas.io We are building Ragas: open-source evaluation & continual improvement framework for RAG & LLM applications 🚀
GIF
30K