falken, 1 month ago to ai

I open sourced a thing !

A super simple web GUI for @mozilla 's #llamafile

Should pass the SO test.

https://codeberg.org/falken/simple-gpt

#ai #linux #chatgpt #llamacpp

stlhood, 1 month ago to random

New blog post! #llamafile: four months of progress towards democratizing AI: https://future.mozilla.org/news/llamafile-four-months-of-progress-towards-democratizing-ai/

governa, 2 months ago to random

#Llamafile 0.7 Brings AVX-512 Support: 10x Faster Prompt Eval Times For AMD Zen 4

https://www.phoronix.com/news/Llamafile-0.7

itnewsbot, 3 months ago to ArtificialIntelligence

A Straightforward AI Voice Assistant, On a Pi - With AI being all the rage at the moment it’s been somewhat annoying that using a ... - https://hackaday.com/2024/02/20/a-straightforward-ai-voice-assistant-on-a-pi/ #artificialintelligence #raspberrypi #llamafile #llama #llm

ErikJonker, 5 months ago to llm

Playing around with small LLM's on my very old laptop using Llamafile , all those models are totally unreliable, hallucinate a lot. Not surprising if you think about how relatively small they are, my resources etc. This is fun to play around with and you can easily change the settings use another model etc. As a learning experience great, for practical use i will stick with ChatGPT4 .
https://github.com/Mozilla-Ocho/llamafile
#llamafile #experiment #llm #AI

ErikJonker, 5 months ago to llm

Nog nooit echt plezier gehad van glasvezel met Gigabit snelheid maar nu wel fijn met het downloaden van Mixtral-8x7B-Instruct , 30 GB 😆
https://github.com/Mozilla-Ocho/llamafile
#LLM #opensource #Mixtral #Llamafile

ErikJonker, 5 months ago (edited 5 months ago) to ai

Amazing, with #Llamafile everybody can experiment with a large language model on their own computer, it's maybe not up to the level of GPT4 but still amazing, running on local resources. My laptop is four years old 🙂
https://github.com/Mozilla-Ocho/llamafile
#AI #experiment #opensource #llama #generativeAI

happyborg, 6 months ago to llm

Try a local #LLM using #Mozilla's #Llamafile:

1. Get the 4.3GB file:
   curl -LO https://huggingface.co/jartine/llava-v1.5-7B-GGUF/resolve/main/llava-v1.5-7b-q4-server.llamafile

2. Make executable

3. Run it

4. Visit http://127.0.0.1:8080/

You're welcome!

This is a text and image capable LLM, so ~ #ChatGPT 4

h/t @simon

More in Simon's blog: https://simonwillison.net/2023/Nov/29/llamafile/

devinprater, 6 months ago to ai

Well, I'm sure an NVDA addon with this will be here soon. Just amazing how far things have come. I mean, I hope there's a Windows version of the Llava part of this anyway.

llamafile is the new best way to run a LLM on your own computer:

https://simonwillison.net/2023/Nov/29/llamafile/

#Llava #ai #Llama #LlamaFile #NVDA #windows