4. A code executor
5. A document Retriever
6. Any other agents deployed in the platform By stitching together one or more of these tools, developers can create AI Agents to solve complex tasks. Read more here:
CODE
-
Building AI Agents by Combining Multiple Tools and Executors
By
–
-
Building AI Agents with Human-Like Abilities Using Multiple LLMs
By
–
We built a platform where users can build agents to solve tasks with human-like abilities or even better. 1. Data sources connected to @abacusai 2. An ML optimization model
3. Any LLM, including GPT-3.5, GPT-4, Llama 2, Claude, etc. -
LangChain Framework Course: Building LLM-Powered Applications
By
–
Building LLM-powered applications can be complex at first. @DeepLearningAI_ has been impressed with the LangChain framework, and decided to partner with them to demystify this topic in a short course. @AndrewYNg @hwchase17 Start learning today for free:
-
Audio Data Analysis with AssemblyAI Document Loader
By
–
There's a lot of really cool data in audio files Big shout out to @patloeber and our friends at @AssemblyAI for adding a document loader This allows you to easily pull in and analyze (summarize, question) audio data!
-
Llama 2 Open Source Model for Flexible Bot Development
By
–
If you're creating a bot, this option gives you more flexibility in case the other models don't meet your needs. And since Llama 2 is open source, you don't have to worry about your bot changing behavior or the base model going away in the long term. (2/2)
-
Outdated Tutorial: Updated Transformers Documentation Available
By
–
It's a pretty old tutorial now – i think there is more up to date material in the transformers documentation for instance cc @stevhliu in case you have a link handy!
-
PDEs Enable Direct Solution Validation From Equations
By
–
With PDEs, you can check if a solution is valid or not, directly from the equation
-
CodeLlama PR merged with 4-bit quantization inference benchmarks
By
–
The CodeLlama PR just got merged: https://
github.com/Lightning-AI/l
it-gpt/pull/472
… When I tried it with bnb's 4-bit Normal Float quantization, the 34B Instruct and Python variants used about 20 Gb for inference: -
Create Your Own AutoTrain Advanced Space and Train Models
By
–
Create your own AutoTrain Advanced Space and start training models!!!
-
ML Replaces Hand-Written Heuristics in Compilers
By
–
There's a huge opportunity to use ML to replace hand-written heuristics in compilers. Want to try? Check out this @kaggle contest organized by Ashley Chow, Bryan Perozzi, HCL-Jevster, inversion, Mangpo Phothilimthana, and Sami Abu-El-Haija!