Running
5
🔍
QwQ-32B-Preview
QwQ-32B-Preview
SambaNova Systems
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
sambanovasystems's activity
kz919
updated
a
Space
9 days ago
kz919
updated
a
Space
16 days ago
kz919
authored
a
paper
26 days ago
Amitabhab
updated
a
Space
26 days ago
kz919
updated
2
Spaces
about 2 months ago
kz919
updated
a
Space
2 months ago
Post
1252
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
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
Post
1283
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
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
Post
1293
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
Try out SambaNova's lightning fast API for free at https://sambanova.ai/fast-api?api_ref=444868
Post
2447
"It's Sunday night, fancy a game?"
https://kz919-can-you-beat-405b-in-chess.hf.space/
built with the one and only SN fast API:
https://sambanova.ai/fast-api?api_ref=907266
https://kz919-can-you-beat-405b-in-chess.hf.space/
built with the one and only SN fast API:
https://sambanova.ai/fast-api?api_ref=907266
- 7 replies
Post
636
Good lord... Spent almost a day debugging this and it turns out it was an issue of gradio update incompatible with the new fastapi.
https://discuss.huggingface.co/t/huggingface-space-failed-after-working-initially/105514/8
Finally got it back online! Come chat with your favorite anime characters here:
kz919/Persona-AI
https://discuss.huggingface.co/t/huggingface-space-failed-after-working-initially/105514/8
Finally got it back online! Come chat with your favorite anime characters here:
kz919/Persona-AI
Post
1586
Spent a few minutes to build an alternative to Character AI on top of llama3.1 405B through SambaNova's super fast inference API
Space: kz919/Persona-AI
API referral link: https://sambanova.ai/fast-api?api_ref=907266
Space: kz919/Persona-AI
API referral link: https://sambanova.ai/fast-api?api_ref=907266
- 3 replies
Post
1688
The only 405B spaces still freely accessible are powered by SN fast api.
xianbao/SambaNova-fast
https://sambanova.ai/fast-api?api_ref=907266
xianbao/SambaNova-fast
https://sambanova.ai/fast-api?api_ref=907266
Post
1811
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.
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
yongningsheng
authored
a
paper
7 months ago
Post
890
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)
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)
daweih
authored
a
paper
7 months ago
kz919
authored
a
paper
7 months ago