DB ddv01

Abusing AI graphical & nlp tools to feed creative addiction and hyperactive curiosity. creator of & Imaginarium comic

[DB ddv01 @Dbddv01]

WIP - Experimental AI LLM gradio UI chatbot for GGUF with a twist, enabling anyone to chain prompts piloted by a csv and more... https://t.co/ohTVPGL0V1 @huggingface @Gradio @ggerganov @abetlen @TheBlokeAI @takyon @GrantSlatton

[DB ddv01 @Dbddv01]

https://t.co/dTQaYk0fr0

[DB ddv01 @Dbddv01]

@doesdatmaksense Maybe check this : https://t.co/STDZCcka0b

[Bezmiar @Bezmiar1]

I found pieces of myself in someone else’s dream.

[Daniel van Strien @vanstriendaniel]

BioMistral is a new 7B foundation model for medical domains, based on Mistral and further trained PubMed Central.
- top open-source medical Large Language Model (LLM) in its weight class
- Apache License
- includes base models, fine tunes, and quantized versions.

[DB ddv01 @Dbddv01]

@huggingface @Gradio @ggerganov @abetlen @TheBlokeAI @takyon @GrantSlatton

[DB ddv01 @Dbddv01]

WIP - Experimental AI LLM gradio UI chatbot for GGUF with a twist, enabling anyone to chain prompts piloted by a csv and more... https://t.co/ohTVPGL0V1 @huggingface @Gradio @ggerganov @abetlen @TheBlokeAI @takyon @GrantSlatton

[tokenbender @tokenbender]

Does 2 bit quantization excite you?
Well it excites me. Imagine the knowledge of the world encoded in 00, 01, 10, 11 sequences. My own model, codeCherryPop, is perfectly coherent and reasons at 2bit as well.

"QuIP: 2-Bit Quantization of Large Language Models With Guarantees" is one such amazing paper discussing how 2 bit quantization performance is spectacular for models

[DB ddv01 @Dbddv01]

@AIEntrepre213 @icreatelife yes, only stable diffusion.

[DB ddv01 @Dbddv01]

@icreatelife Greetz from my country where 9nth art has it's own museum ;-)

[Yann LeCun @ylecun]

This is huge: Llama-v2 is open source, with a license that authorizes commercial use!

This is going to change the landscape of the LLM market.
Llama-v2 is available on Microsoft Azure and will be available on AWS, Hugging Face and other providers

Pretrained and fine-tuned models are available with 7B, 13B and 70B parameters.

Llama-2 website: https://t.co/PKrrXgHdem
Llama-2 paper: https://t.co/aINNrXNhMb

A number of personalities from industry and academia have endorsed our open source approach: https://t.co/N7HwgW9Suh

[AK @_akhaliq]

OpenLLaMA 13B Released

model: https://t.co/n1vUb2I9wx

present a permissively licensed open source reproduction of Meta AI's LLaMA large language model. We are releasing 3B, 7B and 13B models trained on 1T tokens. We provide PyTorch and JAX weights of pre-trained OpenLLaMA models, as well as evaluation results and comparison against the original LLaMA models.

[Nous Research @NousResearch]

Nous-Hermes-13b fp16 weights have been released.

Totallly uncensored, over 300,000 GPT-4 outputs, on base LLaMA.

We’re proud to compete with modern models with this release as we use it as our current basis for tool+agent-based finetuned models.

https://t.co/jrO4XIGhtW

[DB ddv01 @Dbddv01]

@mishig25 to add to the list : https://t.co/ubJCUiH3PL

[Andrei @abetlen]

Just got the new microsoft guidance project working with the llama.cpp via the drop-in openai server.

Start up the web server and change a couple of environment variables and you're good to go, example notebook here:
https://t.co/hfZCvhQ1KX

[DB ddv01 @Dbddv01]

@DrJimFan looks like similar ideas @GrantSlatton 👉 https://t.co/UZlPAcnWJ7

[Grant Slatton @GrantSlatton]

Added arbitrary context free grammar constraints to llama.cpp

Can now plug in any llama.cpp compatible model and give an exact grammar spec: JSON, etc

Excited to use with more powerful local models as they are released

Thanks @ggerganov & friends for such a wonderful project.

[Grant Slatton @GrantSlatton]

Added arbitrary context free grammar constraints to llama.cpp

Can now plug in any llama.cpp compatible model and give an exact grammar spec: JSON, etc

Excited to use with more powerful local models as they are released

Thanks @ggerganov & friends for such a wonderful project.

[DB ddv01 @Dbddv01]

#AIart is too serious ? Luckily, #FoolDiffusion comic is here. pls RT if you 😃. Drawed with #stablediffusion #comics #webcomics #comicstrip #digitalart #cartoon #aiartcommunity #bandedessinee #ComicArt #funnytwitter #twitterhumor #aiia #chatgpt

[Databricks AI Research @DbrxMosaicAI]

📢 Introducing MPT: a new family of open-source commercially usable LLMs from @MosaicML. Trained on 1T tokens of text+code, MPT models match and - in many ways - surpass LLaMa-7B. This release includes 4 models: MPT-Base, Instruct, Chat, & StoryWriter (🧵)
https://t.co/Zg7PcrQvOi

[Together AI @togethercompute]

The first RedPajama models are here! The 3B and 7B models are now available under Apache 2.0 license, including instruction-tuned and chat versions!
This project demonstrates the power of the open-source AI community with many contributors ... 🧵 https://t.co/msO4afBQEK

[DB ddv01 @Dbddv01]

Run local Vicuna-v1-7b model, at 16 token/sec output speed, on my win pc 6gb vram (gx1060). Model in 3bit and <3gb size. Thanks to https://t.co/VH4qfdFytW ! Quality of int3 still to be assessed but already worth to keep an eye on... easy install!