#
Zmu-paramount
Follow
Lists (32)
Agent Stuff
6 repositories
Audio
13 repositories
Code ML
Repos related to source code understanding and generation1 repository
Confidence/Conformal Prediction
Estimating uncertainty and confidence for LLM response scoring1 repository
Datasets
16 repositories
Diffusion/ImageGen
Diffusers, LoRA, ComfyUI stuff4 repositories
Embedding Stuff
1 repository
Frontend/UI
10 repositories
Grammars
22 repositories
Graphs
KG/Graphs/Ontologies LLM, Multimodal etc21 repositories
Important
Libraries in use23 repositories
LangChain/RAG
16 repositories
LLM Efficiency
for the GPU poor4 repositories
LLM Evaluation/Scoring
5 repositories
LLM Serving
6 repositories
LLM UIs
3 repositories
LLMs
NLP/LLM tools, frameworks, libraries for - Deploying/serving LLMs - Structured I/O (e.g. constrained decoding) - Optimization (e.g. quantization) - Fine-tuning58 repositories
LoRaX Deployment
3 repositories
Misc. Cool Repos
64 repositories
MLOps
4 repositories
Movie Narrative Understanding
Research papers and tools related to movie-specific tasks: - semantic segmentation (e.g. scene boundary detection) - action recognition - content moderation etc82 repositories
Multimodal
73 repositories
Prompt Optimization
4 repositories
Recos
3 repositories
Rust
2 repositories
Speaker Diarization/Recognition
5 repositories
SSMs
6 repositories
Synthetic Data
Generation of synthetic datasets5 repositories
Topic Modeling/NLP
8 repositories
Transfer Learning/LoRA
14 repositories
Utils
52 repositories
Video Transformers
80 repositories
Starred repositories
Leveraging DSPy for AI-driven task understanding and solution generation, the Self-Discover Framework automates problem-solving through reasoning and code generation.
Agentic components of the Llama Stack APIs
The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…
Flipper Zero Unleashed Firmware
Utilities intended for use with Llama models.
Official Implementation of "The Surprising Effectiveness of Multimodal Large Language Models for Video Moment Retrieval"
Fully-featured, beautiful web interface for Ollama LLMs - built with NextJS. Deploy with a single click.
A fast inference library for running LLMs locally on modern consumer-class GPUs
A Python wrapper around HuggingFace's TGI (text-generation-inference) and TEI (text-embedding-inference) servers.
Composio equips agents with well-crafted tools empowering them to tackle complex tasks
A new markup-based typesetting system that is powerful and easy to learn.
General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.
Bring portraits to life in Real Time！onnx/tensorrt support！
[ACL 2023] One Embedder, Any Task: Instruction-Finetuned Text Embeddings
[WWW'2024] "RLMRec: Representation Learning with Large Language Models for Recommendation"
TypeScript generator for llama.cpp Grammar directly from TypeScript interfaces
Easy to maintain open source documentation websites.
Distributed LLM inference for mobile, desktop and server.
Building LLM apps with Text Tensors using PyTorch concepts and text gradients
Official implementation of "Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers"
DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models. 🤖💤
