Hugging Face's logo
Zoltan Csaki's picture
48 8 54

Zoltan Csaki

zolicsaki
HolyTreeCrowns's profile picture jackyai2024's profile picture AyoubChLin's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a Space 26 days ago
sambanovasystems/Pictionary
liked a Space about 2 months ago
KingNish/Live-Video-Chat
liked a model about 2 months ago
sbintuitions/sarashina2-70b
View all activity

Organizations

SambaNova Systems's profile picture Social Post Explorers's profile picture

zolicsaki's activity

Reacted to kz919's post with 🚀 2 months ago
view post
Post
1257
Just for the meme.

But the clear lesson I learnt from building these demos are, the more powerful the underlying base model is, the closer you will get to GPT4o1. CoT is nothing more than simply inducing the latent reasoning capability from the model.

kz919/GPT4-O1-Proximas
Reacted to KingNish's post with 👍 2 months ago
posted an update 2 months ago
view post
Post
1247
We’ve open-sourced an app, powered by SambaNova Cloud and Llama 405B, that intelligently detects when a web search is needed—then answers directly or with RAG.

sambanovasystems/auto-web-search

🥚 A hidden Easter egg is that Auto Search detection is already trained into Llama 3.1 checkpoints. Simply use the tool usage system prompt below, and the model will either respond with a web search query if it deems necessary or respond to the query directly.🥚

Environment: IPython
Tools: Brave Search
Knowledge Cutoff Date: December 2023
Today's Date: September 2024
You are a helpful assistant. Reminder:
Search function calls MUST follow the specified format: "brave_search.call(query)"

You can see the documentation here
https://www.llama.com/docs/model-cards-and-prompt-formats/llama3_1#built-in-tooling
and read about how the tool usage was trained into Llama3.1 models in section 4.3.5 here https://arxiv.org/pdf/2407.21783
posted an update 2 months ago
view post
Post
1287
Fast inference is no longer a nice-to-have demo; it will be the driving force behind future frontier models. Time to switch over to custom AI hardware and short Nvidia.

Try out SambaNova's lightning fast API for free at https://sambanova.ai/fast-api?api_ref=444868
Reacted to kz919's post with 🧠🤯🤗🔥🚀😎 3 months ago
Reacted to their post with 🤗 3 months ago
view post
Post
1809
You can run Llama405B at over 100 tokens per second for free using SambaNova's API! https://sambanova.ai/fast-api?api_ref=444868

I have been able to generate some high quality synthetic data and use it as an LLM as a judge instead of the slower and more expensive alternatives like openAI or Anthropic.

  • 2 replies
·
replied to their post 3 months ago
view reply

@gghfez all you need is a valid email, I think they send out the API keys once a day when they approve you. They approve everyone unless they think its a spam trying to get more then one key
Reacted to their post with 🚀 3 months ago
view post
Post
1809
You can run Llama405B at over 100 tokens per second for free using SambaNova's API! https://sambanova.ai/fast-api?api_ref=444868

I have been able to generate some high quality synthetic data and use it as an LLM as a judge instead of the slower and more expensive alternatives like openAI or Anthropic.

  • 2 replies
·
posted an update 3 months ago
view post
Post
1809
You can run Llama405B at over 100 tokens per second for free using SambaNova's API! https://sambanova.ai/fast-api?api_ref=444868

I have been able to generate some high quality synthetic data and use it as an LLM as a judge instead of the slower and more expensive alternatives like openAI or Anthropic.

  • 2 replies
·
Reacted to akhaliq's post with 👍 6 months ago
view post
Post
20832
Chameleon

Mixed-Modal Early-Fusion Foundation Models

Chameleon: Mixed-Modal Early-Fusion Foundation Models (2405.09818)

We present Chameleon, a family of early-fusion token-based mixed-modal models capable of understanding and generating images and text in any arbitrary sequence. We outline a stable training approach from inception, an alignment recipe, and an architectural parameterization tailored for the early-fusion, token-based, mixed-modal setting. The models are evaluated on a comprehensive range of tasks, including visual question answering, image captioning, text generation, image generation, and long-form mixed modal generation. Chameleon demonstrates broad and general capabilities, including state-of-the-art performance in image captioning tasks, outperforms Llama-2 in text-only tasks while being competitive with models such as Mixtral 8x7B and Gemini-Pro, and performs non-trivial image generation, all in a single model. It also matches or exceeds the performance of much larger models, including Gemini Pro and GPT-4V, according to human judgments on a new long-form mixed-modal generation evaluation, where either the prompt or outputs contain mixed sequences of both images and text. Chameleon marks a significant step forward in a unified modeling of full multimodal documents.
posted an update 6 months ago
view post
Post
888
SambaNova just released a revolutionary paper about how the SN40L AI chip can host many LLMs on a single node and run inference so efficiently that it enables running a "composition of experts." These experts can be interconnected via a router, resulting in remarkable accuracy. This method allows you to take open source expert models from HuggingFace and continuously build and integrate them into a composition of experts.

I am also super excited about the possibilities that SN40Ls unlock for LLM agent workflows and pipelined calls. With the release of GPT4o, it seems that monolithic LLMs are starting to reach a plateau, and I believe that the next wave of AI will be driven by pipelined LLM calls and agent workflows. Most pipelined LLM workflows are bottlenecked by prohibitively expensive compute and high latency, but the SN40L provides a one stop shop solution for this. We need to get the word out to the community that this hardware exists, because it will open up a realm of possibilities that developers working with Nvidia hardware did not know exist.

SambaNova SN40L: Scaling the AI Memory Wall with Dataflow and Composition of Experts (2405.07518)
Reacted to not-lain's post with 🔥👍 7 months ago
Reacted to their post with 🚀 7 months ago
posted an update 7 months ago