Over the weekend, I added a GMail ChatLoader integration to @langchain
, to help anyone to finetune models on their emails I evaluated it the old fashioned way – the eyeball test Here's how it did responding to various types of inquiries (VC, customer, integration, @swyx
)
OPEN SOURCE
-
Gmail ChatLoader Integration for Email Model Finetuning
By
–
-
Meta Publishes Research Paper on SeamlessM4T Translation Model
By
–
In the interest of open science and sharing our research, we've published a paper outlining the work on our recently released SeamlessM4T all-in-one multilingual & multimodal translation model. Read the full paper https://
bit.ly/44uzanK -
LLM Finetuning Event Recording Available Now
By
–
Recording for Saturday's LLM Finetuning event is here! https://
youtu.be/S7o_ITTAh8w Grateful to @langchain @brevdev @replicatehq @anyscalecompute @metaphorsystems @_FireworksAI @phindsearch and everyone who came and hacked! (recording turned out bad unfortunately so unlisted fn) -
Code Llama Variants Surpass GPT-4 on HumanEval
By
–
Code Llama was just released 4 days ago. Since then, we already got 1) WizardCoder-34B (
https://
github.com/nlpxucan/Wizar
dLM/tree/main/WizardCoder
…)
2) Phind's finetuned CodeLLama-34B (
https://
phind.com/blog/code-llam
a-beats-gpt4
…) *Both reported to be surpassing GPT-4 on HumanEval. The open source community is amazing! -
Academic Contributions to AI Despite Resource Constraints
By
–
Probably 90% of academia operates under that constraint, and lots of useful insights and contributions (although maybe not models) still come from academia. Alpaca, LIMA, FlashAttention, QLoRA … to name a few innovations from academia.
-
Meta Releases Code Llama Foundation Models Family Open Source
By
–
Meta releases the Code Llama foundation models family in open source https://actuia.com/actualite/meta-publie-la-famille-de-modeles-de-fondation-code-llama-en-open-source/
… #AI #artificialintelligence
@Meta -
Code Llama 34B Instruct Now Available on Hugging Chat
By
–
Code Llama: Now on Hugging Chat 💻🦙
— Hugging Face (@huggingface) 28 août 2023
Try out the 34B Instruct model for free with super fast inference!
👉 https://t.co/TQ0ZaVZcdi pic.twitter.com/Vovq91thG2Code Llama: Now on Hugging Chat Try out the 34B Instruct model for free with super fast inference! http://
hf.co/chat -
Timeline-Based Data Structure for Personal Event RAG Queries
By
–
Just saw a talk by @AlonHalevy about using a **timeline** based data-structure to do RAG. Really useful for querying over personal events Need to dive into this more! Am always excited to see novel data-structures Repo here: https://
github.com/facebookresear
ch/personal-timeline/tree/main
… -
Giraffe: Extended Context Length LLMs from Llama Base Models
By
–
5/ Giraffe – new models that are fine-tuned from base Llama and Llama 2; extends the context length to 4K, 16K, and 32K; explores the space of expanding context lengths in LLMs so it also includes insights useful for practitioners and researchers.
-
SeamlessM4T: Unified Multilingual Multimodal Machine Translation System
By
–
3/ SeamlessM4T – a unified multilingual and multimodal machine translation system that supports ASR, text-to-text translation, speech-to-text translation, text-to-speech translation, and speech-to-speech translation.