I made it using Transformers agents. You can find all the code under "files" in the Space, in file "
http://
app.py"
It uses llama3.1-70B, which would be too heavy to run on a consumer machine, but you can use our API as I did in the space!
LLMS
-
Building applications with Transformer agents and Llama 3.1
By
–
-
1T AI Model Upscaled: Technical Report Released
By
–
Yes, I'm planning to play with it a little 🙂 I've shared the 1T model that was upscaled yesterday, the technical report is an interesting read, I recommend it
-
Interactive LLM Decoding Strategies and Sampling Effects
By
–
Interactive LLM decoding strategies LLM sampling is a cool app that shows the effect of temperature, top K sampling, top P sampling, etc. on the probability distribution outputted by an LLM. LLM sampling: https://
artefact2.github.io/llm-sampling/i
ndex.xhtml
… -
A real-life preview of SearchGPT speed
By
–
A real life preview example of SearchGPT and how fast it is 👀👀👀 https://t.co/D6GM2hD9dO
— 🚨 AI News | TestingCatalog (@testingcatalog) 27 juillet 2024A real life preview example of SearchGPT and how fast it is
-
Comparing AI search tool output quality
By
–
The answer seems quite similar to what you get from Perplexity. Note that it is a Media tab and likely the full answer might be different
-
Tenstorrent Brings Llama-3.1-70B Inference Support to 8-Chip Systems
By
–
We are happy to announce that we have brought up support for Llama-3.1-70B inference on Tenstorrent’s 8-chip systems, the TT-QuietBox and the TT-LoudBox. The source code for Llama-3.1-70B and other models that are supported is on our GitHub —>
-
Advanced Retrieval-Augmented Generation Techniques Explained
By
–
Zain Hasan – Advanced Retrieval-Augmented Generation Techniques https://
bit.ly/3XSK0o8
#AI #MachineLearning #DeepLearning #LLMs #DataScience -
Anthropic developing ‘Source Citations’ feature for knowledge base integration
By
–
BREAKING: Anthropic is working on the "Source Citations" feature. It seems it is meant to collect relevant citations from the Project knowledge base, which might be very useful for researchers. It is yet unclear if it can be a sign of a "web search" functionality
-
Project knowledge base limits constrained by LLM context windows
By
–
Currently the size of the project knowledge based is capped by the max context window Hopefully we will get a bigger one soon