Where to try LLaMA-2(so far): ◆ LLaMa Chat via Perplexity(nice clean interface and super fast, 7B model): https://
llama.perplexity.ai ◆ Demo on Hugging Face(70B): https://
huggingface.co/spaces/ysharma
/Explore_llamav2_with_TGI
…
@jeande_d
-
Where to Try LLaMA-2: Perplexity and Hugging Face Demos
By
–
-
LLaMA-2 Models Available on Hugging Face with Fine-tuning Support
By
–
Update: All 12 LLaMA-2 models(base models + RLHF tuned models) are on Hugging Face. ◆ Quick text-generation inference with transformers
◆ Supported on HF inference endpoints
◆ Script to fine-tune(with PEFT) LLaMA-2 on your own dataset(
https://
gist.github.com/younesbelkada/
9f7f75c94bdc1981c8ca5cc937d4a4da
…) -
LLaMA-2 Release: Open Source AI Model with Commercial Rights
By
–
Wow, LLaMA-2 is out! Love that it is open source and is open for commercial applications. This version is also tuned with RLHF which suggest it will be good for conversational uses cases. LLaMA-2 was trained on 40% more data than LLaMA-1 and has double context length(4K now).
-
Perceiver IO: Unified Neural Network for Multiple Modalities
By
–
"Life would be drastically simpler if a single neural network architecture could handle a wide variety of both input modalities and output tasks." – Perceiver IO
-
Tech Stack Mix: Transformers, Langchain, OpenAI API Without Dolly
By
–
Looks like it’s mix: Transformers , Langchain, Open AI API, etc… Probably no Dolly.
-
Databricks Course: Building Production-Ready LLM Applications
By
–
[NEW COURSE ] Large Language Models: Application through Production, Databricks Really nice course that teaches how to build LLMs powered applications. The course aims at building end-to-end LLM production-ready workflows. Love how course is divided into over 65 byte-sized
-
AI Deadlines tool helps track conferences and submission deadlines
By
–
Lately, I have been looking for tools that keep tracks of AI conferences and corresponding deadlines. Came to find AI Deadlines by amazing Papers With Code. AI Deadlines looks sufficiently enough and hope it stays up to date. http://
aideadlin.es -
Guide for LLM-Powered Chart and Image Generation Systems
By
–
An excellent guide on working with LLM-powered chart and image generation systems!!
-
Lost in the Middle: Research Paper on LLM Context Processing
By
–
Paper: https://
arxiv.org/abs/2307.03172
Code: https://
nelsonliu.me/papers/lost-in
-the-middle
… Work from people at Stanford & UC Berkeley & Samaya AI. By @nelsonfliu
, Kevin Lin, @johnhewtt
, Ashwin Paranajape, @MicheleBevila20
, @Fabio_Petroni
, @percyliang -
Language Models Struggle with Long Context Information
By
–
Lost in the Middle: How Language Models Use Long Contexts Understanding how language models use long contexts is one of the biggest unknowns in language modeling. A recent paper “Lost in the Middle: How Language Models Use Long Contexts” studied this question with utmost rigour