giganttheo's Stars
unslothai/unsloth
Finetune Llama 3.2, Mistral, Phi & Gemma LLMs 2-5x faster with 80% less memory
ScrapeGraphAI/Scrapegraph-ai
Python scraper based on AI
OpenBMB/MiniCPM-V
MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone
VikParuchuri/surya
OCR, layout analysis, reading order, table recognition in 90+ languages
huggingface/lerobot
🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning
kingoflolz/mesh-transformer-jax
Model parallel transformers in JAX and Haiku
huggingface/distil-whisper
Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.
huggingface/safetensors
Simple, safe way to store and distribute tensors
google-research/t5x
godot-jolt/godot-jolt
Godot Jolt is a Godot extension that integrates the Jolt physics engine
NVlabs/VILA
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
mlfoundations/dclm
DataComp for Language Models
xhluca/bm25s
Fast lexical search library implementing BM25 in Python using Numpy and Scipy
prometheus-eval/prometheus-eval
Evaluate your LLM's response with Prometheus and GPT4 💯
IntelLabs/RAGFoundry
Framework for enhancing LLMs for RAG tasks using fine-tuning.
huggingface/text-clustering
Easily embed, cluster and semantically label text datasets
Yale-LILY/SummEval
Resources for the "SummEval: Re-evaluating Summarization Evaluation" paper
huggingface/local-gemma
Gemma 2 optimized for your local machine.
kongds/MoRA
MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning
neulab/BARTScore
BARTScore: Evaluating Generated Text as Text Generation
prometheus-eval/prometheus
[ICLR 2024 & NeurIPS 2023 WS] An Evaluator LM that is open-source, offers reproducible evaluation, and inexpensive to use. Specifically designed for fine-grained evaluation on a customized score rubric, Prometheus is a good alternative for human evaluation and GPT-4 evaluation.
adalkiran/llama-nuts-and-bolts
A holistic way of understanding how Llama and its components run in practice, with code and detailed documentation.
huggingface/data-is-better-together
Let's build better datasets, together!
OpenGVLab/MM-NIAH
[NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents.
ByungKwanLee/TroL
[EMNLP 2024] Official PyTorch implementation code for realizing the technical part of Traversal of Layers (TroL) presenting new propagation operation to get super vision language performances.
Yxxxb/VoCo-LLaMA
VoCo-LLaMA: This repo is the official implementation of "VoCo-LLaMA: Towards Vision Compression with Large Language Models".
catie-aq/flashT5
A fast implementation of T5/UL2 in PyTorch using Flash Attention
nyu-mll/SQuALITY
Query-focused summarization data
google/spiqa
Code release for "SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers"
atharsefid/Extractive_Research_Slide_Generation_Using_Windowed_Labeling_Ranking