Pinned Repositories
a11yAuto
Demonstrations of automated accessibility testing techniques
actor-critic-public
The source code for "An Actor Critic Algorithm for Structured Prediction"
adversarial_image_defenses
Countering Adversarial Image using Input Transformations.
Adversarial_Video_Generation
A TensorFlow Implementation of "Deep Multi-Scale Video Prediction Beyond Mean Square Error" by Mathieu, Couprie & LeCun.
dc_tts
A TensorFlow Implementation of DC-TTS: yet another text-to-speech model
magphase
MagPhase Vocoder: Speech analysis/synthesis system for TTS and related applications.
ProsodyExps
Integrating Prosody Tagger with Festival
world_merlin
build voice using merlin and WORLD vocoder using clustergen linguistic features
pbaljeka's Repositories
pbaljeka/a11yAuto
Demonstrations of automated accessibility testing techniques
pbaljeka/agency-swarm
The only reliable agent framework built on top of the latest OpenAI Assistants API.
pbaljeka/AI-Scientist
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
pbaljeka/ASTRA.ai
A lightning-fast workflow builder, it supports multimodal interaction, highly customizable extensions, and is intuitive to use even without any coding knowledge.
pbaljeka/awesome-ai-security
A collection of awesome resources related AI security
pbaljeka/Awesome-GPT-Agents
A curated list of GPT agents for cybersecurity
pbaljeka/awesomeMLSys
An ML Systems Onboarding list
pbaljeka/conditional-flow-matching
TorchCFM: a Conditional Flow Matching library
pbaljeka/CosyVoice
Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.
pbaljeka/cover-letter-builder
A simple multi-agent workflow for tailoring a cover letter to a specific job based on your skills/experience.
pbaljeka/deepeval
The LLM Evaluation Framework
pbaljeka/FreeAskInternet
FreeAskInternet is a completely free, PRIVATE and LOCALLY running search aggregator & answer generate using MULTI LLMs, without GPU needed. The user can ask a question and the system will make a multi engine search and combine the search result to LLM and generate the answer based on search results. It's all FREE to use.
pbaljeka/giskard
🐢 Open-Source Evaluation & Testing for LLMs and ML models
pbaljeka/gpt-researcher
GPT based autonomous agent that does online comprehensive research on any given topic
pbaljeka/GPU-Puzzles
Solve puzzles. Learn CUDA.
pbaljeka/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
pbaljeka/invariant
A trace analysis tool for AI agents.
pbaljeka/JailbreakZoo
pbaljeka/langflow
⛓️ Langflow is a visual framework for building multi-agent and RAG applications. It's open-source, Python-powered, fully customizable, model and vector store agnostic.
pbaljeka/lectures
Material for cuda-mode lectures
pbaljeka/llm-structured-output-benchmarks
Benchmark various LLM Structured Output frameworks: Instructor, Mirascope, Langchain, LlamaIndex, Fructose, Marvin, Outlines, etc on tasks like multi-label classification, named entity recognition, synthetic data generation, etc.
pbaljeka/NegotiationArena
pbaljeka/nnsight
The nnsight package enables interpreting and manipulating the internals of deep learned models.
pbaljeka/openai-function-calling
Helper functions to generate JSON schema dicts for OpenAI ChatGPT function calling requests.
pbaljeka/simli-deepgram-conversational-demo
Simli - Deepgram Conversational AI demo
pbaljeka/speech-to-speech
pbaljeka/textgrad
Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.
pbaljeka/uptrain
UpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them.
pbaljeka/valor
Valor is a centralized evaluation store which makes it easy to measure, explore, and rank model performance.
pbaljeka/whistleblower
Whistleblower is a tool for leaking system prompts and capability discovery of any API accessible LLM App. Built for developers, security red-teams and folks who want to know what's going on inside the LLM App they use daily