LLM
/llm1881
A space to discuss large language models, AI agents, and how they could interact with Farcaster data
Forget about ChatGPT, just use open source local llm's https://lmstudio.ai/
One of my favorite things about commercial LLMs like Claude is that I can tell it use ChronVer (a spec I published after being tired of SemVer many years ago) and it just does it.
Just started using OAI’s o1-preview model via the api. Seems to be very capable.
It fixed some code I was having trouble with in one shot. And built a working application with code examples in another one shot.
The 32k token output is a game changer.
It fixed some code I was having trouble with in one shot. And built a working application with code examples in another one shot.
The 32k token output is a game changer.
Any leads on LLMs that can add the exact text to an image? Building something & looking for some help...
Claude is the new Clippy
Even pretty censored local LLM models are mostly following instructions if one manually writes the first 1-2 words of the response and only lets them complete from there.
Would be interesting to use a small (uncensored) model to automate that process.
Would be interesting to use a small (uncensored) model to automate that process.
Feeling like this right now because I might finally get access to an EC2 instance that's powerful enough to be a RAG server.
Has anyone else wants a suggestion for a better alternative products of webui for running LLMs locally?here’s the answer:
Nowadays large language models (LLMs) have revolutionized various domains. However, deploying these models in real-world applications can be challenging due to their high computational demands. This is where vLLM steps in. vLLM stands for Virtual Large Language Model and is an active open-source library that supports LLMs in inferencing and model serving efficiently.
Please do refer to vLLM architecture 👇🏻 @bigdegenenergy.eth
Nowadays large language models (LLMs) have revolutionized various domains. However, deploying these models in real-world applications can be challenging due to their high computational demands. This is where vLLM steps in. vLLM stands for Virtual Large Language Model and is an active open-source library that supports LLMs in inferencing and model serving efficiently.
Please do refer to vLLM architecture 👇🏻 @bigdegenenergy.eth
Is RAG still a thing? Or are we doing something else now?
Last time I touched these a few months ago, RAG was OK. And by OK I mean shitty. I was about to start exploring different text embedders to get better search results but I put the project on hold.
Before I resurrect that old project, wanted to see what all the cool kids were up to
Last time I touched these a few months ago, RAG was OK. And by OK I mean shitty. I was about to start exploring different text embedders to get better search results but I put the project on hold.
Before I resurrect that old project, wanted to see what all the cool kids were up to
What is the largest concern for #ai ? Electricity or Hallucination ?
anyone know of alternative products to webui for running LLMs locally?
Ollama through the command line is so much faster compared to webui. seconds vs minutes running the same model. running the anthropic api in webui is way faster than the local LLMs.
Have 2 4090s so power is not a problem for the 7B models. I'm sure it has something to do with my settings. using it out of the box at the moment.
curious to know if anyone else has the same experience.
Ollama through the command line is so much faster compared to webui. seconds vs minutes running the same model. running the anthropic api in webui is way faster than the local LLMs.
Have 2 4090s so power is not a problem for the 7B models. I'm sure it has something to do with my settings. using it out of the box at the moment.
curious to know if anyone else has the same experience.
Alr imma bite, with grok headed right and gpt et al up in their cozy left bubble, who is creating a centrist LLM?
When you're working with a Google AI model and you need truthful answers
Is there a LLM available to consumers that can read developer docs from a URL, and take prompts for what to do with the information, like write code to interface with an api?
WHAT AM I PAYING YOU FOR??
My only complaint about the current state of LLMs when it comes to "mission critical" questions:
"I apologize for not being clearer about the source of that information. As an AI language model, I don't have direct access to external sources or a real-time database."
"I apologize for not being clearer about the source of that information. As an AI language model, I don't have direct access to external sources or a real-time database."
The new display of available image styles in @venice-ai is really great.
Of course, there are much more than these six.
Of course, there are much more than these six.
This is how I feel when using @venice-ai: well protected and in a great place. Venice Pro give me access to excellent open source models for cheaper than OpenAI (but not as much multimodal features for now).
https://venice.ai/chat?ref=FAZRhA
https://venice.ai/chat?ref=FAZRhA
Is this our cue to start getting worried
https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/
https://deepmind.google/discover/blog/ai-solves-imo-problems-at-silver-medal-level/
what is net new about this? what foundational models do you think his company is using? thoughts on focusing on manga first?
TLDR colin kaepernick announces end-to-end media and generative-AI storytelling company Lumi to help creators build, publish, own, and monetize their own stories
- subscription-based distribution platform with a rev share plan (for physical products and merchandise); pricier sub tier provides more access to AI features
- wants to first win manga creators and their fans (turning lumi into manga content platform itself) before expanding
techcrunch.com/2024/07/24/colin-kaepernick-launches-ai-startup-help-creators-storytelling/
TLDR colin kaepernick announces end-to-end media and generative-AI storytelling company Lumi to help creators build, publish, own, and monetize their own stories
- subscription-based distribution platform with a rev share plan (for physical products and merchandise); pricier sub tier provides more access to AI features
- wants to first win manga creators and their fans (turning lumi into manga content platform itself) before expanding
techcrunch.com/2024/07/24/colin-kaepernick-launches-ai-startup-help-creators-storytelling/
Meta releases the biggest and best open-source AI model yet / Llama 3.1 outperforms OpenAI and other rivals on certain benchmarks. Now, Mark Zuckerberg expects Meta’s AI assistant to surpass ChatGPT’s usage in the coming months.
Anyone found any great new use cases for the new 405b meta ai model? Used it a bit and seems kinda meh, but I bet there is a way to use it to unlock something great
Sequoia believes there is a $600B debt owed by Web2 AI and its reaching a tipping point.
The web2 AI narrative is moving towards how revenue will be earned by AI. The obvious route is how the application layer will evolve. (Evident by people's expectations
@EthCC). Sequoia believes there is a $600B shortfall to revenues earned (Right now Web2 AI is about $4B ARR, with @openAI earning a majority $3.4B)
Perhaps we should focus our attention on how today's problems can be solved with AI instead of just developing AI for the sake of AGI...
With more applications built with AI we will have a future with AGI thats supported by thriving businesses.
https://sequoiacap.com/article/ais-600b-question/
The web2 AI narrative is moving towards how revenue will be earned by AI. The obvious route is how the application layer will evolve. (Evident by people's expectations
@EthCC). Sequoia believes there is a $600B shortfall to revenues earned (Right now Web2 AI is about $4B ARR, with @openAI earning a majority $3.4B)
Perhaps we should focus our attention on how today's problems can be solved with AI instead of just developing AI for the sake of AGI...
With more applications built with AI we will have a future with AGI thats supported by thriving businesses.
https://sequoiacap.com/article/ais-600b-question/