tugglep

Preston Tuggle's starred repositories

ToolQA

ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.

Language:Jupyter NotebookApache-2.022800

anthropic-cookbook

A collection of notebooks/recipes showcasing some fun and effective ways of using Claude.

Language:Jupyter NotebookMIT393900

lm-evaluation-harness

A framework for few-shot evaluation of language models.

Language:PythonMIT606100

gritlm

Generative Representational Instruction Tuning

Language:Jupyter NotebookMIT50000

anthropic-on-aws

Language:Jupyter NotebookMIT-01900

Meta-Llama-on-AWS

Language:Jupyter NotebookMIT-03500

Cohere-on-AWS

Language:Jupyter NotebookMIT-01500

crewAI

Framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Language:PythonMIT1798700

cookbook

Language:Jupyter NotebookMIT103400

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Language:Jupyter NotebookMIT2404300

mistral-finetune

Language:PythonApache-2.0258600

mistral-on-aws

Mistral on AWS examples for Bedrock & SageMaker

Language:Jupyter NotebookMIT-03700