My personal collection of interesting models I've quantized from the past week (yes, just week)
So you don't have to click the link, here's the full text including links:
Some of my favourite @huggingface models I've quantized in the last week (as always, original models are linked in my repo so you can check out any recent changes or documentation!):
@shishirpatil_ gave us gorilla's openfunctions-v2, a great followup to their initial models: https://huggingface.co/bartowski/gorilla-openfunctions-v2-exl2
@fanqiwan released FuseLLM-VaRM, a fusion of 3 architectures and scales: https://huggingface.co/bartowski/FuseChat-7B-VaRM-exl2
@IBM used a new method called LAB (Large-scale Alignment for chatBots) for our first interesting 13B tune in awhile: https://huggingface.co/bartowski/labradorite-13b-exl2
@NeuralNovel released several, but I'm a sucker for DPO models, and this one uses their Neural-DPO dataset: https://huggingface.co/bartowski/Senzu-7B-v0.1-DPO-exl2
Locutusque, who has been making the Hercules dataset, released a preview of "Hyperion": https://huggingfac
Interesting, hadn't heard of it before today, but guess I don't look at European car brands that often anyways
Ah I mean fair enough :) I don't keep up much with car brands and ownerships, but still TIL haha
Huh, didn't realize Volvo was primarily owned by a Chinese company, you got me there lol, genuinely always thought they were standalone and therefore a Swedish company
Colour me intrigued. I want more manufactures that go against the norm. If they put out a generic slab with normal specs at an expected price, I won't be very interested, but if they do something cool I'm all for it
Except I just noticed the part where it's developed by Meizu so nevermind probably will be a generic Chinese phone
itsme2417/PolyMind: A multimodal, function calling powered LLM webui.
A multimodal, function calling powered LLM webui. - GitHub - itsme2417/PolyMind: A multimodal, function calling powered LLM webui.
PolyMind is a multimodal, function calling powered LLM webui. It's designed to be used with Mixtral 8x7B + TabbyAPI and offers a wide range of features including:
Internet searching with DuckDuckGo and web scraping capabilities.
Image generation using comfyui.
Image input with sharegpt4v (Over llama.cpp's server)/moondream on CPU, OCR, and Yolo.
Port scanning with nmap.
Wolfram Alpha integration.
A Python interpreter.
RAG with semantic search for PDF and miscellaneous text files.
Plugin system to easily add extra functions that are able to be called by the model. 90% of the web parts (HTML, JS, CSS, and Flask) are written entirely by Mixtral.
Nomic releases a 8192 Sequence Length Text Embedder that outperforms OpenAI text-embedding-ada-002 and text-embedding-v3-small.
Open source
Open data
Open training code
Fully reproducible and auditable
Pretty interesting stuff for embeddings, I'm going to try it for my RAG pipeline when I get a chance, I've not had as much success as I was hoping, maybe this english-focused one will help
InternLM2 models llama-fied
Thanks to Charles for the conversion scripts, I've converted several of the new internLM2 models into Llama format. I've also made them into ExLlamaV2 while I was at it.
You can find them here:
https://huggingface.co/bartowski?search_models=internlm2
Note, the chat models seem to do something odd without outputting [UNUSED_TOKEN_145] in a way that seems equivalent to <|im_end|>, not sure why, but it works fine despite outputting that at the end.
WizardLM/WizardCoder-33B-V1.1 released!
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Based off of deepseek coder, the current SOTA 33B model, allegedly has gpt 3.5 levels of performance, will be excited to test once I've made exllamav2 quants and will try to update with my findings as a copilot model
I live in Ontario where we go down to -30C in the harshest conditions.
We have a heat pump and a furnace and they alternate based on efficiency
Somewhere around -5 to +5 C it switches from the heat pump to the furnace
I think you could get by a bit colder but it really loses out on efficiency vs burning gas unless you invest in a geothermal heat pump
Microsoft announces WaveCoder
Paper abstract:
Recent work demonstrates that, after being fine-tuned on a high-quality instruction dataset, the resulting model can obtain impressive capabilities to address a wide range of tasks. However, existing methods for instruction data generation often produce duplicate data and are not controllable enough on data quality. In this paper, we extend the generalization of instruction tuning by classifying the instruction data to 4 code-related tasks and propose a LLM-based Generator-Discriminator data process framework to generate diverse, high-quality instruction data from open source code. Hence, we introduce CodeOcean, a dataset comprising 20,000 instruction instances across 4 universal code-related tasks,which is aimed at augmenting the effectiveness of instruction tuning and improving the generalization ability of fine-tuned model. Subsequently, we present WaveCoder, a fine-tuned Code LLM with Widespread And Versatile Enhanced instruction tuning. This model is specifically
Wtf? This is a weird take lol
Hope it comes out soon that's some nice QOL updates :)
Very interesting they wouldn't let him film the camera bump.. it must have some kind of branding on it like Hasselblad? Or maybe they've secretly found a way to have no bump! One can dream..
Inside The OnePlus Open – And The Machines That Torture It - MrMobile
Beginner questions thread
Yeah definitely need to still understand the open source limits, they're getting pretty dam good at generating code but their comprehension isn't quite there, I think the ideal is eventually having 2 models, one that determines the problem and what the solution would be, and another that generates the code, so that things like "fix this bug" or more vague questions like "how do I start writing this app" would be more successful
Beginner questions thread
I've had decent results with continue, it's similar to copilot and actually works decently with local models lately:
Beginner questions thread
Trying something new, going to pin this thread as a place for beginners to ask what may or may not be stupid questions, to encourage both the asking and answering.
Depending on activity level I'll either make a new one once in awhile or I'll just leave this one up forever to be a place to learn and ask.
When asking a question, try to make it clear what your current knowledge level is and where you may have gaps, should help people provide more useful concise answers!
By far the biggest pain point of Sony.. their software is clean stable and fast, with acceptable release cadence, but their promise of 2 years is completely unacceptable in this day
Wish there was any way at all to influence them
Not a glowing review that this is accidentally not a reply to a comment. :p
Yeah I guess I meant more it just doesn't get nearly as much attention, but you're right there's some starting and that's quite nice
My biggest problem with vaping is that there's basically no distinction made between ecigarettes that this article addresses and vaping dry herbs.. would love to read up on it and any possible health concerns but rarely see it discussed
Not much detail in the article but at least it's not set for phones for now
Does it not? I've never received a single spam message on telegram in my 6 years of use :S
In this update, we launch Stories – with a unique dual camera mode, granular privacy settings, flexible duration options and much more.
TodayAugust 23rd, Telegram celebrates its 10th birthday – with our biggest update yet. Over the past decade we’ve built hundreds of new features that are now used by over 800 million people. In this update, we launch Stories – with a unique dual camera mode, granular privacy settings, flexible duration options and much more
Even Sony dropped theirs, miss it so much
Thanks for the comment! Yes this is meant more for your personal projects than for using in existing projects
The idea behind needing a password to get a password, totally understand, my main goal was to have local encrypted storage, the nice thing about this implementation is that you can have all your env files saved and shared in your git repo for all devs to have access to, but only can decrypt it if given the master password shared elsewhere (keeper, vault etc) so you don't have to load all values from a vault, just the master
100% though this doesn't cover a large range of usage, hence the name "simple" haha, wouldn't be opposed to expanding but I think it covers my proposed use cases as-is
SimpleSecretsManager: A python library to manage encrypted secrets
A python library to manage encrypted secrets. Contribute to noneabove1182/SimpleSecretsManager development by creating an account on GitHub.
Not your typical self-hosted kind of project, but useful for other self-hosted projects
For myself, I had been storing critical values like passwords and tokens in my .env file and just loading them up with load_dotenv()
I got frustrated that I couldn't find a relatively native python library that didn't require calling restful APIs and wasn't just reading from plaintext, so finally decided to put on that gauntlet and say "Fine, I'll do it myself"
Please feel free to use or fork for your own needs :) And let me know if this is a silly endeavour or you see any major issues! It's very barebones and simple (hence the name)
definitely for sure this time we promise
Best place to host a lemmy wiki
Wanting to make a wiki for /c/localllama, but not sure if there's a known place that's nice for making free wikis, anyone got suggestions on what's being used widely on lemmy?
For people self hosting LLMs.. I have a couple docker images I maintain
https://github.com/noneabove1182/text-generation-webui-docker (updated to 1.3.1 and has a fix for gqa to run llama2 70B)
https://github.com/noneabove1182/lollms-webui-docker (v3.0.0)
https://github.com/noneabove1182/koboldcpp-docker (updated to 1.36)
All should include up to date instructions, if you find any issues please ping me immediately so I can take a look or open an issue :)
Given Samsung's six month flagship release schedule, it’s always been a safe bet that the Galaxy Flip 5 and Galaxy Fold 5 are in the offing.
Nothing Phone 2 Camera specs
𝗥𝗲𝗮𝗿: • 50MP (Sony IMX890) (f/1.9) (1/1.56") (OIS & EIS) Focal length: 24mm
• 50MP (Samsung JN1) (f/2.2) (1/2.7") (EIS) (FoV: 115°) Macro (4cm)
𝗦𝗲𝗹𝗳𝗶𝗲: 32MP (Sony IMX615) (f/2.4) (EIS)
The upcoming Google Pixel 8 Pro looks set to gain DisplayPort support over USB-C. Here's what you need to know about it.
Exciting moving forward, hopefully it leads to display port being standard on Android
Pixel tablet review megathread
Wanted to compile reviews for everyone to see
Articles
The Verge https://www.theverge.com/23765921/google-pixel-tablet-review
TechRadar https://www.techradar.com/reviews/google-pixel-tablet-review-a-new-home-for-the-same-old-android
Mobile Syrup https://mobilesyrup.com/2023/06/20/google-pixel-tablet-review/
Wired https://www.wired.com/review/google-pixel-tablet/
CNET https://www.cnet.com/tech/computing/google-pixel-tablet-review-android-tablets-are-back/
Android Authority https://www.androidauthority.com/google-pixel-tablet-hands-on-3323546/
ARS Technica https://arstechnica.com/gadgets/2023/05/googles-pixel-tablet-looks-just-like-a-smart-display-so-why-isnt-it-one/
Tom's Guide https://www.tomsguide.com/reviews/google-pixel-tablet
Android Police https://www.androidpolice.com/google-pixel-tablet-review/
Videos
MKBHD https://youtu.be/aT
Customers in Belgium, France, Germany, Italy, Netherlands, Poland, Spain, Sweden and the UK can make a self-repair on their Samsung Galaxy devices
Customers in Belgium, France, Germany, Italy, Netherlands, Poland, Spain, Sweden and the UK can make a self-repair on their Samsung Galaxy devices
Samsung Galaxy Watch6 prices in France
Découvrez, en exclusivité, les prix des montres connectées Galaxy Watch 6 et Watch 6 Classic de Samsung ! Obtenez tous les détails ici.
Watch6 - Graphite and Cream €319.99 €369.99 (LTE)
Watch6 Classic - Graphite and Silver €349.99 €399.99 (LTE)