SivilTaram

Persona-Dialogue-Generation

The code of ACL 2020 paper "You Impress Me: Dialogue Generation via Mutual Persona Perception"

code-html-to-markdown

A lightweight script for processing HTML page to markdown format with support for code blocks

CHASE

Synthetic Data Generation for Evaluation

OctoThinker

Revisiting Mid-training in the Era of Reinforcement Learning Scaling

santacoder-finetuning-commit

Fine-tune SantaCoder for Code/Text Generation.

simpleRL-reason

This is a replicate of DeepSeek-R1-Zero and DeepSeek-R1 training on small models with limited data

SivilTaram.github.io

axolotl

Go ahead and axolotl questions

bytepiece

更纯粹、更高压缩率的Tokenizer

catwalk

This project studies the performance and robustness of language models and task-adaptation methods.

dclm

DataComp for Language Models

dl4c.github.io

Deep Learning for Code Website

dl4c.github.io-1

✨ Build a beautiful and simple website in literally minutes. Demo at https://beautifuljekyll.com

extract-expert

Extract a single expert from an MoE model of Mixtral architecture, using slerp

imp

infinigen

Infinite Photorealistic Worlds using Procedural Generation

Megatron-LLM

distributed trainer for LLMs

mergekit

Tools for merging pretrained large language models.

oat

🌾 OAT: Online AlignmenT for LLMs

OpenAgents

OpenAgents: An Open Platform for Language Agents in the Wild

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Precision-RL

Defeating the Training-Inference Mismatch via FP16

sailcraft

Data Toolkit for Sailor Language Models

SivilTaram

steplaw

surya

Accurate line-level text detection and recognition (OCR) in any language

TinyLlama

The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

Triton-Puzzles

Puzzles for learning Triton

verl-pipeline

Async pipelined version of Verl

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs